diff --git a/CHANGELOG.md b/CHANGELOG.md index 0a8f5b0..ca4d9ad 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,39 @@ # Changelog — Tether +## [0.7.1-beta.1] - 2026-11-12 + +Beta release for testing the changes since `0.7.0`, available on the Beta update channel. This is the first build on Electron 45. + +### New Features +- **Native OpenCode usage** - local OpenCode sessions now count toward the same totals, daily/model/environment breakdowns, budgets, pane details and exports as Claude Code and Codex. Usage is read from OpenCode's own database (read-only), including cache/reasoning tokens and CLI-reported cost; legacy Crush databases are still supported (#282). +- **Local theme packs** - add full JSON themes under Tether's `themes` folder. Appearance lists them beside the built-in themes, with **Open themes folder** and **Reload themes** actions (#279). +- **Docked subagent transcripts** - clicking a subagent row opens its transcript in a resizable panel beside the terminals instead of a modal dialog. The panel follows a running agent and keeps final answers whole up to 200,000 characters (#326). +- **More quota detail** - show model-scoped weekly Claude limits such as Fable, and show free Codex rate-limit resets with a confirmed **Use reset** action (#322, #323). +- **Pip polish** - Pip wakes for permission prompts and waiting sessions, no longer blanks its lines, counts only real typing, and reacts to long turns, crashes and helpers. New off-by-default **Operational nudges** cover Vault expiry, quota, budgets and updates (#327, #329, #330, #332). +- **Pip AI quips through Claude** - the AI quips setting is now a chooser: Off, Codex or Claude (Claude subscription, Haiku, no tools, hooks or saved history). Late replies get their own display window, and cooldowns are enforced in main. **Share submitted prompts** names the recipient and now covers local OpenCode sessions (#333, #334, #335). + +### Bug Fixes +- **Quit guard** - closing the window now asks first when a session is starting, running or waiting on a permission prompt. The window is shown on a fallback timer if the GPU compositor never reports ready, so Tether can no longer run invisibly (#307). +- **Claude credentials are read-only** - the quota service no longer refreshes or rewrites `~/.claude/.credentials.json` (#306). +- **Status detection** - handle Claude's failure, idle and session-switch hooks, and add bounded fallbacks so a hook-driven session doesn't get stuck on "running" (#310). +- **Recoverable remove, restart and undo** - **Restart all** starts each replacement before removing the original, and undo/remove can no longer lose a session (#311). +- **Focus and shortcuts** - focus can no longer land on a hidden pane, along with other status and shortcut fixes (#308). +- **Create dialogs stay open on failure** - New Session and New Environment keep what you typed when creation fails, and a worktree created for a failed launch is cleaned up (#314). +- **Windows npm-shim launches** - Codex and OpenCode launch directly through their npm shims, so initial prompts and Helm briefs containing quotes work (#313). +- **Session creation during shutdown** - quitting, removing or force-killing a starting session cancels its creation instead of leaving an unowned process (#289). +- **Less disk churn** - Tether no longer rewrites `data.json` every time a session changes state (#305). +- **Pricing for new models** - a model newer than the pricing table is priced from its nearest known version rather than Sonnet-class defaults (#309). +- **Remote usage probe** - resolve `node` even when the remote login profile aliases it (#328). +- **OpenCode** - restore Windows conversation discovery for npm installs, and keep known conversation IDs when restarting SSH/Coder sessions (#278, #281). + +### Security and Internal +- Scope Helm's status/kill tools to the sessions that Helm session spawned, accept OSC 52 clipboard writes only from the focused pane, and harden webhook tokens (#312). +- Upgrade to Electron 45, Vitest 5.1 and current dependency/action versions. Move build tooling off ReDoS-prone `minimatch`/`ip-address` releases (#303, #304, #315-#321). +- Run SonarQube JS/TS rules locally through ESLint, clear new Sonar issues and add test coverage (#324, #325, #331). Strengthen dependency, Windows smoke and release checks in CI (#280). +- Refresh the bundled pricing snapshot used for offline API-cost estimates. + +--- + ## [0.7.0] — 2026-10-15 Stable release graduating the 0.6.x beta train, the first stable milestone since `0.6.1-hotfix.1`. Runtime code and bundled pricing match `0.6.10-beta.9`; this promotion updates release metadata and documentation. diff --git a/package-lock.json b/package-lock.json index 1e2e99b..6d90836 100644 --- a/package-lock.json +++ b/package-lock.json @@ -1,12 +1,12 @@ { "name": "tether", - "version": "0.7.0", + "version": "0.7.1", "lockfileVersion": 3, "requires": true, "packages": { "": { "name": "tether", - "version": "0.7.0", + "version": "0.7.1", "hasInstallScript": true, "license": "MIT", "dependencies": { diff --git a/package.json b/package.json index 88e7a63..443a60f 100644 --- a/package.json +++ b/package.json @@ -1,7 +1,7 @@ { "name": "tether", "productName": "Tether", - "version": "0.7.0", + "version": "0.7.1", "description": "A unified control plane for managing agent CLI sessions across local, remote, and containerized environments.", "main": ".vite/build/index.js", "private": true, diff --git a/src/main/usage/litellm-prices.json b/src/main/usage/litellm-prices.json index 3d3846c..d90d3cd 100644 --- a/src/main/usage/litellm-prices.json +++ b/src/main/usage/litellm-prices.json @@ -1,4 +1,172 @@ { + "azure/gpt-realtime-2.1-2026-07-07": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-06-25", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image_token": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 2.4e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "cache_read_input_image_token_cost": 5e-07, + "supports_prompt_caching": true, + "supports_reasoning": true + }, + "azure/gpt-realtime-2.1-mini-2026-07-07": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 6e-08, + "deprecation_date": "2027-06-25", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_audio_token": 1e-05, + "input_cost_per_image_token": 8e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "cache_read_input_image_token_cost": 8e-08, + "supports_prompt_caching": true, + "supports_reasoning": true + }, + "azure/gpt-realtime-translate-2026-05-06": { + "input_cost_per_second": 0.0005666666666666667, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/a-new-chapter-for-realtime-ai-reasoning-translation-and-real-time-transcription/4517124", + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "audio", + "text" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_native_streaming": true + }, + "azure/gpt-realtime-translate-2026-05-07": { + "input_cost_per_second": 0.0005666666666666667, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://ai.azure.com/catalog/models/gpt-realtime-translate", + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "audio", + "text" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_native_streaming": true + }, + "azure/gpt-realtime-whisper-2026-05-06": { + "input_cost_per_second": 0.0002833333333333333, + "litellm_provider": "azure", + "mode": "audio_transcription", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper", + "supported_endpoints": [ + "/v1/realtime", + "/v1/realtime/transcription_sessions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "max_input_tokens": 32000, + "max_output_tokens": 4096 + }, + "azure/gpt-realtime-whisper-2026-05-07": { + "input_cost_per_second": 0.0002833333333333333, + "litellm_provider": "azure", + "mode": "audio_transcription", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper", + "supported_endpoints": [ + "/v1/realtime", + "/v1/realtime/transcription_sessions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "max_input_tokens": 32000, + "max_output_tokens": 4096 + }, "sample_spec": { "code_interpreter_cost_per_session": 0.0, "computer_use_input_cost_per_1k_tokens": 0.0, @@ -9,9 +177,8 @@ "input_cost_per_audio_token": 0.0, "input_cost_per_token": 0.0, "litellm_provider": "one of https://docs.litellm.ai/docs/providers", - "max_input_tokens": "max input tokens, if the provider specifies it. if not default to max_tokens", - "max_output_tokens": "max output tokens, if the provider specifies it. if not default to max_tokens", - "max_tokens": "LEGACY parameter. set to max_output_tokens if provider specifies it. IF not set to max_input_tokens, if provider specifies it.", + "max_input_tokens": "max input tokens, if the provider specifies it", + "max_output_tokens": "max output tokens, if the provider specifies it", "mode": "one of: chat, embedding, completion, image_generation, audio_transcription, audio_speech, image_generation, moderation, rerank, search", "output_cost_per_reasoning_token": 0.0, "output_cost_per_token": 0.0, @@ -41,6 +208,7 @@ }, "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0": { "deprecation_date": "2026-09-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", @@ -49,37 +217,132 @@ "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.018 }, "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.036 }, + "abliteration/abliterated-model": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "abliteration", + "max_input_tokens": 262144, + "max_output_tokens": 262134, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://abliteration.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ] + }, + "abliteration/abliterated-model-large": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "abliteration", + "max_input_tokens": 1000000, + "max_output_tokens": 999990, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://abliteration.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ] + }, + "abliteration/abliterated-model-large-v2": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "abliteration", + "max_input_tokens": 1000000, + "max_output_tokens": 999990, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://abliteration.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "reasoning_effort_levels": [ + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ] + }, + "abliteration/abliterated-model-large-flash": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "abliteration", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://abliteration.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ] + }, "ai21.j2-mid-v1": { "input_cost_per_token": 1.25e-05, "litellm_provider": "bedrock", "max_input_tokens": 8191, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.25e-05, "source": "https://aws.amazon.com/bedrock/pricing/" @@ -89,29 +352,28 @@ "litellm_provider": "bedrock", "max_input_tokens": 8191, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.88e-05, "source": "https://aws.amazon.com/bedrock/pricing/" }, "ai21.jamba-1-5-large-v1:0": { "deprecation_date": "2026-11-26", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-large.md", "input_cost_per_token": 2e-06, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-large.md" }, "ai21.jamba-1-5-mini-v1:0": { "deprecation_date": "2026-11-26", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-mini.md", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-mini.md" @@ -121,7 +383,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 70000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -278,6 +539,7 @@ }, "amazon.nova-canvas-v1:0": { "deprecation_date": "2026-09-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", @@ -286,6 +548,7 @@ }, "us.amazon.nova-canvas-v1:0": { "deprecation_date": "2026-09-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", @@ -293,23 +556,25 @@ "supports_nova_canvas_image_edit": true }, "us.writer.palmyra-x4-v1:0": { + "deprecation_date": "2027-03-09", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "input_cost_per_token": 2.5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "supports_function_calling": true, "supports_pdf_input": true }, "us.writer.palmyra-x5-v1:0": { + "deprecation_date": "2027-03-21", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", @@ -317,23 +582,25 @@ "supports_pdf_input": true }, "writer.palmyra-x4-v1:0": { + "deprecation_date": "2027-03-09", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "input_cost_per_token": 2.5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "supports_function_calling": true, "supports_pdf_input": true }, "writer.palmyra-x5-v1:0": { + "deprecation_date": "2027-03-21", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", @@ -342,26 +609,31 @@ }, "writer.palmyra-vision-7b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, "output_cost_per_token_flex": 3e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_vision": true }, "amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, + "output_cost_per_token_batches": 1.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -371,13 +643,18 @@ }, "amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_priority": 1.3125e-07, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -392,13 +669,16 @@ "input_cost_per_token": 1.25e-06, "input_cost_per_image_token": 1.25e-06, "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.1875e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://aws.amazon.com/nova/pricing/", + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 1.75e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -414,7 +694,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.311e-06, "supports_function_calling": true, @@ -434,7 +713,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://aws.amazon.com/nova/pricing/", @@ -453,7 +731,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.597e-06, "supports_function_calling": true, @@ -473,7 +750,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://aws.amazon.com/nova/pricing/", @@ -489,15 +765,20 @@ "us.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 8.25e-08, "cache_read_input_token_cost_flex": 4.125e-08, + "cache_read_input_token_cost_priority": 1.44375e-07, "input_cost_per_token": 3.3e-07, + "input_cost_per_token_batches": 1.65e-07, "input_cost_per_token_flex": 1.65e-07, + "input_cost_per_token_priority": 5.775e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-06, + "output_cost_per_token_batches": 1.375e-06, "output_cost_per_token_flex": 1.375e-06, + "output_cost_per_token_priority": 4.8125e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -512,13 +793,16 @@ "input_cost_per_token": 1.375e-06, "input_cost_per_image_token": 1.375e-06, "input_cost_per_audio_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.40625e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.1e-05, - "source": "https://aws.amazon.com/nova/pricing/", + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 1.925e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -531,7 +815,6 @@ "amazon.nova-2-multimodal-embeddings-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 8172, - "max_tokens": 8172, "mode": "embedding", "input_cost_per_token": 1.35e-07, "input_cost_per_image": 6e-05, @@ -548,12 +831,14 @@ "amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 8.75e-09, "input_cost_per_token": 3.5e-08, + "input_cost_per_token_batches": 1.75e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, + "output_cost_per_token_batches": 7e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, @@ -561,13 +846,18 @@ }, "amazon.nova-premier-v1:0": { "cache_read_input_token_cost": 6.25e-07, + "cache_read_input_token_cost_priority": 1.09375e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_priority": 4.375e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.25e-05, + "output_cost_per_token_batches": 6.25e-06, + "output_cost_per_token_priority": 2.1875e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -578,15 +868,20 @@ "amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 8e-07, + "input_cost_per_token_batches": 4e-07, "input_cost_per_token_flex": 4e-07, + "input_cost_per_token_priority": 1.4e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, + "output_cost_per_token_batches": 1.6e-06, "output_cost_per_token_flex": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -598,9 +893,12 @@ "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 3.3e-07, "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2.75e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-2-sonic.md", "supports_audio_input": true, "supports_audio_output": true }, @@ -610,7 +908,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -619,7 +916,6 @@ "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 128, - "max_tokens": 128, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, @@ -634,7 +930,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 @@ -643,7 +938,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 @@ -652,7 +946,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -684,13 +977,13 @@ }, "twelvelabs.marengo-embed-2-7-v1:0": { "deprecation_date": "2026-11-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_query": 7e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -699,13 +992,13 @@ }, "us.twelvelabs.marengo-embed-2-7-v1:0": { "deprecation_date": "2026-11-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_query": 7e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -714,13 +1007,13 @@ }, "eu.twelvelabs.marengo-embed-2-7-v1:0": { "deprecation_date": "2026-11-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_query": 7e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -734,7 +1027,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, - "max_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, @@ -748,7 +1040,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, - "max_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, @@ -762,7 +1053,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, - "max_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, @@ -770,40 +1060,50 @@ "supports_image_input": true }, "twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "us.twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "eu.twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "global.twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", "supports_video_input": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md" }, "amazon.titan-text-express-v1": { "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 6e-07 }, @@ -812,7 +1112,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 2e-07 }, @@ -821,7 +1120,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, @@ -832,7 +1130,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -852,7 +1149,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", @@ -869,7 +1165,11 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-07, - "output_cost_per_token_batches": 2.5e-06 + "output_cost_per_token_batches": 2.5e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-haiku-4-5@20251001": { "cache_creation_input_token_cost": 1.25e-06, @@ -880,7 +1180,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -896,14 +1195,14 @@ "supports_native_streaming": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "token_count_model": {"model":"anthropic.claude-haiku-4-5-20251001-v1:0","litellm_provider":"bedrock"} }, "anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -911,10 +1210,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 3e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07 }, @@ -923,9 +1218,8 @@ "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -935,11 +1229,7 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 3e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07 + "supports_vision": true }, "anthropic.claude-3-7-sonnet-20240620-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -948,7 +1238,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -968,7 +1257,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -986,7 +1274,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -1001,7 +1288,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true @@ -1010,11 +1296,11 @@ "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2027-01-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -1031,7 +1317,11 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "token_count_model": { + "model": "anthropic.claude-opus-4-1-20250805-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -1040,7 +1330,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -1068,7 +1357,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1090,7 +1378,11 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1103,7 +1395,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1126,7 +1417,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1139,7 +1434,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1162,7 +1456,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1175,7 +1473,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1198,7 +1495,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1211,7 +1512,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1234,7 +1534,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "au.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1247,7 +1551,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1270,7 +1573,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1283,7 +1590,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1308,7 +1614,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "anthropic.claude-mythos-preview": { "cache_creation_input_token_cost": 3.4375e-05, @@ -1319,7 +1630,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, @@ -1341,7 +1651,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1366,7 +1675,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1379,7 +1693,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1404,7 +1717,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1417,7 +1735,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1442,7 +1759,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + } }, "au.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1455,7 +1777,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1480,7 +1801,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, @@ -1490,7 +1816,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1512,13 +1837,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-fable-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.25e-05, @@ -1528,7 +1858,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1567,7 +1896,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1589,13 +1917,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-fable-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.25e-05, @@ -1605,7 +1938,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1629,6 +1961,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -1636,6 +1969,9 @@ "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "bedrock/claude-fable-latest": { + "alias_of": "global.anthropic.claude-fable-5-2" + }, "us.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_1hr": 2.2e-05, @@ -1644,7 +1980,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1666,13 +2001,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-fable-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.375e-05, @@ -1682,7 +2022,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1706,6 +2045,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -1721,7 +2061,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1743,7 +2082,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -1759,7 +2098,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1783,6 +2121,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -1792,6 +2131,7 @@ "anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -1801,7 +2141,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1825,7 +2164,14 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-east-1/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "input_cost_per_token_batches": 2.5e-06, + "output_cost_per_token_batches": 1.25e-05 }, "anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -1839,7 +2185,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "search_context_cost_per_query": { @@ -1865,11 +2210,17 @@ "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -1879,7 +2230,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1899,11 +2249,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-east-1/index.json", + "token_count_model": { + "model": "global.anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "input_cost_per_token_batches": 2.5e-06, + "output_cost_per_token_batches": 1.25e-05 }, "global.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -1917,7 +2275,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "search_context_cost_per_query": { @@ -1937,17 +2294,27 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/", "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "global.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } + }, + "bedrock/claude-opus-latest": { + "alias_of": "global.anthropic.claude-opus-5-5" }, "us.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, @@ -1957,7 +2324,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1977,11 +2343,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-east-1/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.375e-05 }, "us.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -1995,7 +2369,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { @@ -2015,17 +2388,24 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/", "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, @@ -2035,7 +2415,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2055,11 +2434,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/eu-west-1/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + }, + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.375e-05 }, "eu.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -2073,7 +2460,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { @@ -2093,6 +2479,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, @@ -2104,6 +2491,7 @@ "au.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, @@ -2113,7 +2501,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2133,11 +2520,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/ap-southeast-2/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + }, + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.375e-05 }, "au.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -2151,7 +2546,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { @@ -2171,17 +2565,24 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "thinking_always_on": true, "supports_forced_tool_use": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "jp.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, @@ -2191,7 +2592,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2211,11 +2611,14 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/ap-northeast-1/index.json", + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.375e-05 }, "jp.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -2229,7 +2632,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { @@ -2249,6 +2651,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, @@ -2269,7 +2672,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -2289,12 +2691,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2308,7 +2716,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -2328,12 +2735,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2347,7 +2761,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2367,12 +2780,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2386,7 +2806,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2406,12 +2825,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + } }, "au.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2425,7 +2851,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2445,12 +2870,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "jp.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2464,7 +2896,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2484,12 +2915,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, "jp.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -2501,7 +2939,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2526,7 +2963,12 @@ "supports_minimal_reasoning_effort": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, "anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2538,7 +2980,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { @@ -2547,6 +2988,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -2560,12 +3002,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2577,7 +3025,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { @@ -2586,6 +3033,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -2599,12 +3047,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2616,7 +3071,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { @@ -2625,6 +3079,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -2638,12 +3093,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2655,7 +3117,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { @@ -2664,6 +3125,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -2677,12 +3139,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + } }, "au.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2694,7 +3163,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { @@ -2703,6 +3171,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -2716,12 +3185,19 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "jp.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2733,7 +3209,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { @@ -2742,6 +3217,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -2755,6 +3231,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -2773,7 +3251,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -2781,7 +3258,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2795,7 +3272,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2808,7 +3289,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -2816,7 +3296,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2830,7 +3310,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2843,7 +3327,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -2851,7 +3334,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2865,7 +3348,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2878,7 +3365,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -2886,7 +3372,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2900,7 +3386,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "au.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2913,7 +3403,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -2921,7 +3410,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2935,7 +3424,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "jp.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2948,7 +3441,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -2956,7 +3448,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2970,21 +3462,26 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3003,7 +3500,11 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -3016,11 +3517,12 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "deprecation_date": "2027-04-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3042,14 +3544,17 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, "output_cost_per_token_batches": 7.5e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-v1": { "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05 }, @@ -3058,7 +3563,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -3068,7 +3572,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07 }, @@ -3077,7 +3580,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -3086,7 +3588,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" @@ -3096,7 +3597,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" @@ -3106,7 +3606,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07 }, @@ -3115,7 +3614,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -3124,7 +3622,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07 }, @@ -3133,7 +3630,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" @@ -3143,7 +3639,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" @@ -3153,7 +3648,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1", @@ -3164,7 +3658,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1", @@ -3175,7 +3668,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1", @@ -3187,7 +3679,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.52e-07, "supports_function_calling": true, @@ -3203,7 +3694,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.48e-07, "supports_function_calling": true, @@ -3219,7 +3709,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.36e-06, "output_cost_per_token_flex": 1.68e-06, @@ -3238,7 +3727,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -3255,21 +3743,26 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "apac.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "apac.anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3288,7 +3781,11 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "assemblyai/best": { "input_cost_per_second": 3.333e-05, @@ -3313,11 +3810,12 @@ "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "deprecation_date": "2027-04-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "au.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -3339,26 +3837,30 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "azure/ada": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 1e-07, + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/codex-mini": { "cache_read_input_token_cost": 3.75e-07, "deprecation_date": "2026-11-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.5e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -3382,20 +3884,10 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/command-r-plus": { - "deprecation_date": "2025-06-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_function_calling": true - }, "azure_ai/claude-haiku-4-5": { "deprecation_date": "2026-11-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/claude-haiku-5-5", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, @@ -3403,7 +3895,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -3420,6 +3911,8 @@ }, "azure_ai/claude-opus-4-5": { "deprecation_date": "2026-11-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/claude-opus-5-5", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, @@ -3427,8 +3920,12 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, @@ -3440,11 +3937,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, + "supports_web_search": true, "prompt_cache_min_tokens": 4096, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-opus-4-6": { "deprecation_date": "2027-02-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "input_cost_per_token": 5e-06, @@ -3452,7 +3951,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -3473,17 +3971,18 @@ "supports_vision": true, "supports_output_config": true, "supports_max_reasoning_effort": true, + "supports_web_search": true, "prompt_cache_min_tokens": 4096 }, "azure_ai/claude-opus-4-7": { "deprecation_date": "2027-04-06", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_adaptive_thinking": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -3505,17 +4004,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, + "supports_web_search": true, "prompt_cache_min_tokens": 2048 }, "azure_ai/claude-fable-5": { "deprecation_date": "2027-12-05", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_mid_conversation_system": true, "input_cost_per_token": 1e-05, "output_cost_per_token": 5e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -3538,7 +4038,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true, + "supports_max_reasoning_effort": false, + "supports_web_search": true, "prompt_cache_min_tokens": 512 }, "azure_ai/claude-fable-5-1": { @@ -3548,7 +4049,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -3573,63 +4073,35 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true, + "supports_max_reasoning_effort": false, + "supports_web_search": true, "prompt_cache_min_tokens": 512, - "deprecation_date": "2027-12-05" + "deprecation_date": "2027-12-05", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement" }, - "azure_ai/claude-opus-5": { - "deprecation_date": "2027-07-08", - "supports_mid_conversation_system": true, - "supports_adaptive_thinking": true, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, - "litellm_provider": "azure_ai", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "azure_ai/claude-fable-latest": { + "alias_of": "azure_ai/claude-fable-5-2" }, - "azure_ai/claude-opus-5-5": { - "supports_mid_conversation_system": true, - "input_cost_per_token": 4e-06, - "output_cost_per_token": 2e-05, + "azure_ai/claude-mythos-5-1": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 2.5e-07, + "deprecation_date": "2027-09-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "cache_creation_input_token_cost": 5e-06, - "cache_creation_input_token_cost_above_1hr": 8e-06, - "cache_read_input_token_cost": 2e-07, - "deprecation_date": "2027-09-18", "supports_adaptive_thinking": true, "thinking_always_on": true, + "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, @@ -3643,20 +4115,22 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true, + "supports_max_reasoning_effort": false, + "supports_web_search": true, "prompt_cache_min_tokens": 512, - "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" + "source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement" }, - "azure_ai/claude-opus-4-8": { - "deprecation_date": "2027-09-01", + "azure_ai/claude-opus-5": { + "deprecation_date": "2027-07-08", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -3678,10 +4152,87 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, + "supports_web_search": true, + "prompt_cache_min_tokens": 512 + }, + "azure_ai/claude-opus-5-5": { + "supports_mid_conversation_system": true, + "input_cost_per_token": 4e-06, + "output_cost_per_token": 2e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2027-09-18", + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_web_search": true, + "prompt_cache_min_tokens": 512, + "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" + }, + "azure_ai/claude-opus-latest": { + "alias_of": "azure_ai/claude-opus-5-5" + }, + "azure_ai/claude-opus-4-8": { + "deprecation_date": "2027-09-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "supports_mid_conversation_system": true, + "supports_adaptive_thinking": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_web_search": true, "prompt_cache_min_tokens": 1024 }, "azure_ai/claude-sonnet-4-5": { "deprecation_date": "2026-11-30", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/claude-sonnet-5-5", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, @@ -3689,8 +4240,12 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, @@ -3701,11 +4256,13 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, + "supports_web_search": true, "prompt_cache_min_tokens": 1024, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-sonnet-5": { "deprecation_date": "2027-06-30", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, @@ -3714,7 +4271,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { @@ -3723,6 +4279,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -3735,10 +4292,12 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, + "supports_web_search": true, "prompt_cache_min_tokens": 1024 }, "azure_ai/claude-sonnet-4-6": { "deprecation_date": "2027-02-10", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, @@ -3748,10 +4307,14 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -3762,6 +4325,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, + "supports_web_search": true, "prompt_cache_min_tokens": 1024, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models" }, @@ -3770,7 +4334,6 @@ "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -3794,21 +4357,24 @@ "supports_vision": true }, "azure/container": { - "code_interpreter_cost_per_session": 0.03, + "code_interpreter_cost_per_session": 0.033, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure_ai/gpt-oss-120b": { + "deprecation_date": "2027-09-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": false, "supports_response_schema": true, "supports_tool_choice": true }, @@ -3822,7 +4388,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, @@ -3848,7 +4413,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, @@ -3861,6 +4426,9 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure_ai/gpt-astra-latest": { + "alias_of": "azure_ai/gpt-6-astra" + }, "azure_ai/gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, @@ -3871,7 +4439,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, @@ -3910,6 +4477,9 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure_ai/gpt-luna-latest": { + "alias_of": "azure_ai/gpt-6-luna" + }, "azure_ai/gpt-6-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, @@ -3920,7 +4490,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, @@ -3969,7 +4538,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, @@ -3995,7 +4563,58 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure_ai/gpt-sol-latest": { + "alias_of": "azure_ai/gpt-6.1-sol" + }, + "azure_ai/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, @@ -4008,8 +4627,12 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure_ai/gpt-terra-latest": { + "alias_of": "azure_ai/gpt-6.1-terra" + }, "azure_ai/gpt-5.5": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1e-06, @@ -4021,7 +4644,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, @@ -4057,12 +4679,12 @@ }, "azure_ai/gpt-chat-latest": { "cache_read_input_token_cost": 5e-07, - "deprecation_date": "2026-12-02", + "deprecation_date": "2027-05-18", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", - "max_input_tokens": 272000, + "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", @@ -4093,6 +4715,7 @@ "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-10-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", @@ -4108,11 +4731,11 @@ "azure_ai/codex-mini": { "cache_read_input_token_cost": 3.75e-07, "deprecation_date": "2026-11-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", @@ -4138,6 +4761,7 @@ }, "azure_ai/whisper": { "deprecation_date": "2026-12-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_second": 0.0001, "litellm_provider": "azure_ai", "mode": "audio_transcription", @@ -4156,7 +4780,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, @@ -4192,6 +4815,7 @@ }, "azure_ai/gpt-5.5-2026-04-24": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1e-06, @@ -4203,7 +4827,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, @@ -4239,6 +4862,8 @@ }, "azure_ai/gpt-5.4": { "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/gpt-5.5", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_priority": 5e-07, @@ -4250,7 +4875,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, @@ -4287,6 +4911,8 @@ }, "azure_ai/gpt-5.4-2026-03-05": { "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/gpt-5.5", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_priority": 5e-07, @@ -4298,7 +4924,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, @@ -4335,6 +4960,7 @@ }, "azure_ai/gpt-5.4-pro": { "deprecation_date": "2027-09-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "cache_read_input_token_cost_priority": 6e-06, @@ -4346,7 +4972,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -4381,6 +5006,7 @@ }, "azure_ai/gpt-5.4-pro-2026-03-05": { "deprecation_date": "2027-09-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "cache_read_input_token_cost_priority": 6e-06, @@ -4392,7 +5018,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -4427,6 +5052,7 @@ }, "azure_ai/gpt-5.4-mini": { "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, @@ -4434,7 +5060,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_priority": 9e-06, @@ -4467,8 +5092,12 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure_ai/gpt-mini-latest": { + "alias_of": "azure_ai/gpt-5.4-mini" + }, "azure_ai/gpt-5.4-mini-2026-03-17": { "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, @@ -4476,7 +5105,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_priority": 9e-06, @@ -4511,6 +5139,7 @@ }, "azure_ai/gpt-5.4-nano": { "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_priority": 4e-08, "input_cost_per_token": 2e-07, @@ -4518,7 +5147,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_priority": 2.5e-06, @@ -4553,6 +5181,7 @@ }, "azure_ai/gpt-5.4-nano-2026-03-17": { "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_priority": 4e-08, "input_cost_per_token": 2e-07, @@ -4560,7 +5189,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_priority": 2.5e-06, @@ -4595,37 +5223,38 @@ }, "azure_ai/model_router": { "deprecation_date": "2027-05-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.4e-07, "output_cost_per_token": 0, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/", "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/ where deployment-name is your Azure deployment (e.g., azure-model-router)" }, "azure_ai/model-router": { "deprecation_date": "2027-05-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.4e-07, "output_cost_per_token": 0, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/", "comment": "Catalog-name twin of azure_ai/model_router: the flat $0.14 per M input tokens is the router's own fee, the routed model is priced on top of it" }, "azure/eu/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -4637,8 +5266,31 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/eu/gpt-4o": { + "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1", + "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, + "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/eu/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1", "cache_creation_input_token_cost": 1.38e-06, "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, @@ -4646,7 +5298,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -4657,17 +5308,46 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/eu/gpt-4o-mini": { + "cache_read_input_token_cost": 8.3e-08, + "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/eu/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.65e-07, "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -4684,7 +5364,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2.2e-05, "output_cost_per_token": 2.64e-06, @@ -4695,40 +5374,18 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "azure/eu/gpt-4o-realtime-preview-2024-10-01": { - "cache_creation_input_audio_token_cost": 2.2e-05, - "cache_read_input_token_cost": 2.75e-06, - "deprecation_date": "2025-03-26", - "input_cost_per_audio_token": 0.00011, - "input_cost_per_token": 5.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 0.00022, - "output_cost_per_token": 2.2e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "azure/eu/gpt-4o-realtime-preview-2024-12-17": { - "cache_read_input_audio_token_cost": 2.5e-06, + "cache_read_input_audio_token_cost": 2.75e-06, "cache_read_input_token_cost": 2.75e-06, "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" @@ -4748,17 +5405,23 @@ "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_priority": 2.75e-07, "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1", "input_cost_per_token": 1.375e-06, "input_cost_per_token_batches": 6.875e-07, "input_cost_per_token_priority": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -4787,18 +5450,24 @@ "azure/eu/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, "cache_read_input_token_cost_priority": 4.95e-08, - "deprecation_date": "2027-02-09", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.4-mini", "input_cost_per_token": 2.75e-07, "input_cost_per_token_batches": 1.375e-07, "input_cost_per_token_priority": 4.95e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -4825,7 +5494,9 @@ "cache_read_input_token_cost_batches": 1.375e-08 }, "azure/eu/gpt-5.1": { - "deprecation_date": "2027-05-15", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.2", "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_batches": 6.875e-08, "cache_read_input_token_cost_priority": 2.75e-07, @@ -4833,7 +5504,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ @@ -4865,16 +5535,22 @@ "input_cost_per_token_priority": 2.75e-06, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.2-codex", "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -4901,12 +5577,12 @@ }, "azure/eu/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -4934,15 +5610,21 @@ "azure/eu/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5.5e-09, "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.4-nano", "input_cost_per_token": 5.5e-08, "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -4968,15 +5650,34 @@ "supports_vision": true, "cache_read_input_token_cost_batches": 2.75e-09 }, + "azure/eu/o1": { + "cache_read_input_token_cost": 8.25e-06, + "deprecation_date": "2026-11-19", + "successor_model": "azure/eu/gpt-5.6-sol", + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/eu/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", + "successor_model": "azure/eu/gpt-5.6-sol", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, "output_cost_per_token_batches": 3.3e-05, @@ -4994,7 +5695,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, @@ -5004,15 +5704,35 @@ "supports_prompt_caching": true, "supports_vision": false }, + "azure/eu/o3-mini": { + "cache_read_input_token_cost": 6.05e-07, + "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6-terra", + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "azure/eu/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6-terra", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, @@ -5025,12 +5745,12 @@ "azure/global-standard/gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -5045,12 +5765,12 @@ "azure/global-standard/gpt-4o-2024-11-20": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -5063,13 +5783,18 @@ }, "azure/global-standard/gpt-4o-mini": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -5078,13 +5803,14 @@ }, "azure/global/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/global/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -5098,13 +5824,14 @@ }, "azure/global/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/global/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -5117,7 +5844,8 @@ "supports_vision": true }, "azure/global/gpt-5.1": { - "deprecation_date": "2027-05-15", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, @@ -5125,7 +5853,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -5157,16 +5884,21 @@ "input_cost_per_token_priority": 2.5e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-codex": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -5193,12 +5925,12 @@ }, "azure/global/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -5228,184 +5960,110 @@ "litellm_provider": "azure", "max_input_tokens": 4097, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, "supports_tool_choice": true }, "azure/gpt-3.5-turbo-instruct-0914": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, - "max_tokens": 4097, + "max_output_tokens": 4097, "mode": "completion", - "output_cost_per_token": 2e-06 + "output_cost_per_token": 2.2e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-35-turbo": { "input_cost_per_token": 5e-07, "litellm_provider": "azure", "max_input_tokens": 4097, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, "supports_tool_choice": true }, - "azure/gpt-35-turbo-16k": { - "deprecation_date": "2025-04-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "azure", - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-16k-0613": { - "deprecation_date": "2025-04-30", - "input_cost_per_token": 3e-06, - "litellm_provider": "azure", - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", - "supports_function_calling": true, - "supports_tool_choice": true - }, "azure/gpt-35-turbo-instruct": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, - "max_tokens": 4097, + "max_output_tokens": 4097, "mode": "completion", - "output_cost_per_token": 2e-06 + "output_cost_per_token": 2.2e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-35-turbo-instruct-0914": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, - "max_tokens": 4097, + "max_output_tokens": 4097, "mode": "completion", - "output_cost_per_token": 2e-06 - }, - "azure/gpt-4": { - "deprecation_date": "2025-06-06", - "input_cost_per_token": 3e-05, - "litellm_provider": "azure", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 2.2e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-4-0125-preview": { "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, - "azure/gpt-4-0613": { - "deprecation_date": "2025-06-06", - "input_cost_per_token": 3e-05, - "litellm_provider": "azure", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", - "supports_function_calling": true, - "supports_tool_choice": true - }, "azure/gpt-4-1106-preview": { "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, - "azure/gpt-4-32k": { - "deprecation_date": "2025-06-06", - "input_cost_per_token": 6e-05, - "litellm_provider": "azure", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00012, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", - "supports_tool_choice": true - }, - "azure/gpt-4-32k-0613": { - "deprecation_date": "2025-06-06", - "input_cost_per_token": 6e-05, - "litellm_provider": "azure", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00012, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", - "supports_tool_choice": true - }, "azure/gpt-4-turbo": { - "input_cost_per_token": 1e-05, + "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-turbo-2024-04-09": { - "input_cost_per_token": 1e-05, + "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4-turbo-vision-preview": { - "input_cost_per_token": 1e-05, + "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4.1": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, @@ -5414,11 +6072,15 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5444,6 +6106,8 @@ }, "azure/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, @@ -5452,11 +6116,15 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5482,6 +6150,8 @@ }, "azure/gpt-4.1-mini": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-mini", "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, @@ -5490,11 +6160,15 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5520,6 +6194,8 @@ }, "azure/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-mini", "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, @@ -5528,11 +6204,15 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -5558,13 +6238,14 @@ }, "azure/gpt-4.1-nano": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-nano", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -5592,13 +6273,14 @@ }, "azure/gpt-4.1-nano-2025-04-14": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-nano", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -5624,37 +6306,20 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-4.5-preview": { - "cache_read_input_token_cost": 3.75e-05, - "deprecation_date": "2025-07-14", - "input_cost_per_token": 7.5e-05, - "input_cost_per_token_batches": 3.75e-05, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.00015, - "output_cost_per_token_batches": 7.5e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "azure/gpt-4o": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5663,13 +6328,14 @@ "supports_vision": true }, "azure/gpt-4o-2024-05-13": { - "deprecation_date": "2026-12-09", + "deprecation_date": "2027-01-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -5682,13 +6348,14 @@ }, "azure/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -5702,13 +6369,14 @@ }, "azure/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -5722,12 +6390,12 @@ }, "azure/gpt-audio": { "deprecation_date": "2027-03-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, @@ -5742,6 +6410,7 @@ "text", "audio" ], + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5755,12 +6424,12 @@ }, "azure/gpt-audio-2025-08-28": { "deprecation_date": "2027-03-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, @@ -5775,6 +6444,7 @@ "text", "audio" ], + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5787,12 +6457,12 @@ }, "azure/gpt-audio-1.5": { "deprecation_date": "2027-08-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -5807,6 +6477,7 @@ "text", "audio" ], + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5820,12 +6491,12 @@ }, "azure/gpt-audio-1.5-2026-02-23": { "deprecation_date": "2027-08-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -5841,6 +6512,8 @@ "text", "audio" ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5853,12 +6526,12 @@ }, "azure/gpt-audio-mini": { "deprecation_date": "2027-06-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -5873,6 +6546,7 @@ "text", "audio" ], + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5885,12 +6559,12 @@ }, "azure/gpt-audio-mini-2025-10-06": { "deprecation_date": "2027-04-06", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -5905,6 +6579,8 @@ "text", "audio" ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5921,7 +6597,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, @@ -5936,6 +6611,7 @@ "text", "audio" ], + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -5948,14 +6624,22 @@ }, "azure/gpt-4o-mini": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5966,15 +6650,20 @@ "azure/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -5989,7 +6678,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 6e-07, @@ -6005,6 +6693,7 @@ "text", "audio" ], + "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, @@ -6023,7 +6712,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -6035,20 +6723,24 @@ "supports_tool_choice": true }, "azure/gpt-realtime": { + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-03-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "supported_endpoints": [ "/v1/realtime" ], @@ -6067,23 +6759,28 @@ "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure/gpt-realtime-2025-08-28": { + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-03-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "supported_endpoints": [ "/v1/realtime" ], @@ -6104,20 +6801,25 @@ "supports_tool_choice": true }, "azure/gpt-realtime-1.5": { + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-08-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-realtime-2.1-2026-07-07", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "supported_endpoints": [ "/v1/realtime" ], @@ -6136,23 +6838,29 @@ "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure/gpt-realtime-1.5-2026-02-23": { + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-08-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-realtime-2.1-2026-07-07", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "supported_endpoints": [ "/v1/realtime" ], @@ -6175,16 +6883,20 @@ "azure/gpt-realtime-2.1": { "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-06-25", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", @@ -6204,22 +6916,28 @@ "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/gpt-realtime-2.1-mini": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, + "cache_read_input_image_token_cost": 8e-08, "cache_read_input_token_cost": 6e-08, "deprecation_date": "2027-06-25", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", @@ -6239,24 +6957,31 @@ "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/gpt-realtime-mini": { + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "cache_read_input_image_token_cost": 8e-08, "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "deprecation_date": "2027-06-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "supported_endpoints": [ "/v1/realtime" ], @@ -6281,16 +7006,19 @@ "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "deprecation_date": "2027-04-06", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "supported_endpoints": [ "/v1/realtime" ], @@ -6312,6 +7040,7 @@ }, "azure/gpt-4o-mini-transcribe": { "deprecation_date": "2027-06-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", @@ -6325,6 +7054,7 @@ }, "azure/gpt-4o-mini-tts": { "deprecation_date": "2027-06-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 6e-07, "litellm_provider": "azure", "mode": "audio_speech", @@ -6342,39 +7072,18 @@ "audio" ] }, - "azure/gpt-4o-realtime-preview-2024-10-01": { - "cache_creation_input_audio_token_cost": 2e-05, - "cache_read_input_token_cost": 2.5e-06, - "deprecation_date": "2025-03-26", - "input_cost_per_audio_token": 0.0001, - "input_cost_per_token": 5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 0.0002, - "output_cost_per_token": 2e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "azure/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_audio_token_cost": 2.5e-06, "cache_read_input_token_cost": 2.5e-06, "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" @@ -6392,6 +7101,7 @@ }, "azure/gpt-4o-transcribe": { "deprecation_date": "2026-10-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", @@ -6406,6 +7116,7 @@ }, "azure/gpt-4o-transcribe-diarize": { "deprecation_date": "2027-04-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", @@ -6424,8 +7135,10 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "audio_transcription", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper", "supported_endpoints": [ "/v1/realtime", @@ -6442,13 +7155,14 @@ "azure/gpt-5.1-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, - "deprecation_date": "2027-05-15", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.2", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, @@ -6478,6 +7192,11 @@ "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.25e-07, "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_minimal_reasoning_effort": true, "cache_read_input_token_cost_batches": 6.25e-08 @@ -6486,12 +7205,13 @@ "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.2-codex", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, @@ -6521,12 +7241,12 @@ "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2.5e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "output_cost_per_token_priority": 3.6e-06, @@ -6554,6 +7274,8 @@ }, "azure/gpt-5": { "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, @@ -6563,11 +7285,15 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6596,17 +7322,23 @@ "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1", "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6635,11 +7367,12 @@ "azure/gpt-5-codex": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2027-03-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.1-codex", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -6665,7 +7398,9 @@ "supports_vision": true }, "azure/gpt-5-mini": { - "deprecation_date": "2027-02-09", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-mini", "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, @@ -6675,11 +7410,15 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6707,18 +7446,24 @@ "azure/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 4.5e-08, - "deprecation_date": "2027-02-09", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-mini", "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6746,6 +7491,8 @@ }, "azure/gpt-5-nano": { "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-nano", "cache_read_input_token_cost": 5e-09, "cache_read_input_token_cost_batches": 2.5e-09, "input_cost_per_token": 5e-08, @@ -6753,10 +7500,14 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6784,15 +7535,21 @@ "azure/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5e-09, "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4-nano", "input_cost_per_token": 5e-08, "input_cost_per_token_batches": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -6820,15 +7577,21 @@ }, "azure/gpt-5-pro": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.2-pro", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" @@ -6851,7 +7614,9 @@ "supports_vision": true }, "azure/gpt-5.1": { - "deprecation_date": "2027-05-15", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.2", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, @@ -6859,7 +7624,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -6891,16 +7655,22 @@ "input_cost_per_token_priority": 2.5e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -6921,11 +7691,12 @@ "azure/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -6943,11 +7714,12 @@ "azure/gpt-5.2-chat": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.75e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -6964,11 +7736,12 @@ "azure/gpt-5.3-chat": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.75e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -6985,11 +7758,12 @@ "azure/us/gpt-5.1-chat": { "cache_read_input_token_cost": 1.375e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-chat-latest", "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7007,11 +7781,12 @@ "azure/us/gpt-5.2-chat": { "cache_read_input_token_cost": 1.925e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-chat-latest", "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7028,11 +7803,12 @@ "azure/us/gpt-5.3-chat": { "cache_read_input_token_cost": 1.925e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-chat-latest", "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7049,11 +7825,12 @@ "azure/eu/gpt-5.1-chat": { "cache_read_input_token_cost": 1.375e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7071,11 +7848,12 @@ "azure/eu/gpt-5.2-chat": { "cache_read_input_token_cost": 1.925e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7092,11 +7870,12 @@ "azure/eu/gpt-5.3-chat": { "cache_read_input_token_cost": 1.925e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7110,46 +7889,15 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "azure/us/o1-preview": { - "cache_read_input_token_cost": 8.25e-06, - "deprecation_date": "2025-07-28", - "input_cost_per_token": 1.65e-05, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_prompt_caching": true - }, - "azure/eu/o1-preview": { - "cache_read_input_token_cost": 8.25e-06, - "deprecation_date": "2025-07-28", - "input_cost_per_token": 1.65e-05, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6.6e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_prompt_caching": true - }, "azure/gpt-5.1-codex": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.2-codex", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7177,11 +7925,11 @@ "azure/gpt-5.1-codex-max": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2027-05-18", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7208,12 +7956,12 @@ }, "azure/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7240,6 +7988,8 @@ }, "azure/gpt-5.2": { "deprecation_date": "2027-06-08", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4", "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_batches": 8.75e-08, "cache_read_input_token_cost_priority": 3.5e-07, @@ -7249,11 +7999,15 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -7283,17 +8037,23 @@ "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, "deprecation_date": "2027-06-08", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.4", "input_cost_per_token": 1.75e-06, "input_cost_per_token_batches": 8.75e-07, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -7323,11 +8083,12 @@ "azure/gpt-5.2-codex": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.3-codex", "input_cost_per_token": 1.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7356,15 +8117,20 @@ "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, "deprecation_date": "2027-08-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.75e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" @@ -7393,14 +8159,13 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -7432,14 +8197,13 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -7467,6 +8231,8 @@ }, "azure/gpt-5.4": { "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.5", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07, @@ -7481,7 +8247,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, @@ -7525,6 +8290,8 @@ }, "azure/us/gpt-5.4": { "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.5", "cache_read_input_token_cost": 2.75e-07, "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, @@ -7537,7 +8304,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -7575,6 +8341,8 @@ }, "azure/eu/gpt-5.4": { "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.5", "cache_read_input_token_cost": 2.75e-07, "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, @@ -7587,7 +8355,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -7630,6 +8397,8 @@ "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.5", "input_cost_per_token": 2.5e-06, "input_cost_per_token_above_272k_tokens": 5e-06, "input_cost_per_token_priority": 5e-06, @@ -7637,7 +8406,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, @@ -7686,6 +8454,8 @@ "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.5", "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, "output_cost_per_token": 1.65e-05, @@ -7693,7 +8463,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -7736,6 +8505,8 @@ "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "deprecation_date": "2027-09-02", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.5", "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, "output_cost_per_token": 1.65e-05, @@ -7743,7 +8514,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -7783,6 +8553,8 @@ }, "azure/gpt-5.4-pro": { "deprecation_date": "2027-09-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.5-pro", "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "input_cost_per_token": 3e-05, @@ -7794,7 +8566,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -7803,9 +8574,9 @@ "output_cost_per_token_batches": 9e-05, "output_cost_per_token_flex": 9e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -7835,6 +8606,8 @@ "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "deprecation_date": "2027-09-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.5-pro", "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_cost_per_token_above_272k_tokens_flex": 3e-05, @@ -7843,7 +8616,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -7851,9 +8623,9 @@ "output_cost_per_token_batches": 9e-05, "output_cost_per_token_flex": 9e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -7897,16 +8669,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "output_cost_per_token_priority": 4e-05, "output_cost_per_token_above_272k_tokens_priority": 6e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -7949,6 +8720,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, "cache_read_input_token_cost_flex": 2e-07, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-6-sol", "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "input_cost_per_token_above_272k_tokens_flex": 4e-06, @@ -7958,7 +8731,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -7967,9 +8739,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6e-05, "output_cost_per_token_flex": 1e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8013,6 +8785,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, "cache_read_input_token_cost_flex": 2e-07, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-6-sol", "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "input_cost_per_token_above_272k_tokens_flex": 4e-06, @@ -8022,7 +8796,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -8031,9 +8804,9 @@ "output_cost_per_token_above_272k_tokens_priority": 6e-05, "output_cost_per_token_flex": 1e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8077,6 +8850,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, "cache_read_input_token_cost_flex": 1e-07, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-6.1-terra", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "input_cost_per_token_above_272k_tokens_flex": 2e-06, @@ -8086,7 +8861,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, @@ -8095,9 +8869,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, "output_cost_per_token_flex": 6e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8141,6 +8915,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, "cache_read_input_token_cost_flex": 1e-07, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-6.1-terra", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "input_cost_per_token_above_272k_tokens_flex": 2e-06, @@ -8150,7 +8926,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, @@ -8159,9 +8934,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, "output_cost_per_token_flex": 6e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8205,6 +8980,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-6-luna", "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, "input_cost_per_token_above_272k_tokens_flex": 2e-07, @@ -8214,7 +8991,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, @@ -8223,9 +8999,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, "output_cost_per_token_flex": 6e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -8269,6 +9045,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-6-luna", "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, "input_cost_per_token_above_272k_tokens_flex": 2e-07, @@ -8278,7 +9056,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, @@ -8287,9 +9064,9 @@ "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, "output_cost_per_token_flex": 6e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -8330,16 +9107,11 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8356,7 +9128,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8366,7 +9138,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, + "input_cost_per_token_above_272k_tokens_flex": 1e-05, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-05, + "input_cost_per_token_flex": 5e-06, + "output_cost_per_token_flex": 2.5e-05, + "cache_read_input_token_cost_flex": 5e-07, + "cache_creation_input_token_cost_flex": 6.25e-06 + }, + "azure/gpt-astra-latest": { + "alias_of": "azure/gpt-6-astra" }, "azure/gpt-6-astra-2026-09-03": { "cache_creation_input_token_cost": 1.25e-05, @@ -8379,16 +9162,11 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8405,7 +9183,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8415,7 +9193,15 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, + "input_cost_per_token_above_272k_tokens_flex": 1e-05, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-05, + "input_cost_per_token_flex": 5e-06, + "output_cost_per_token_flex": 2.5e-05, + "cache_read_input_token_cost_flex": 5e-07, + "cache_creation_input_token_cost_flex": 6.25e-06 }, "azure/gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, @@ -8428,15 +9214,125 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-07, + "cache_creation_input_token_cost_flex": 6.25e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-08, + "cache_read_input_token_cost_flex": 5e-09, + "input_cost_per_token_above_272k_tokens_flex": 1e-07, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-07, + "output_cost_per_token_flex": 2.5e-07 + }, + "azure/gpt-luna-latest": { + "alias_of": "azure/gpt-6-luna" + }, + "azure/gpt-6-luna-2026-09-22": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-07, + "cache_creation_input_token_cost_flex": 6.25e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-08, + "cache_read_input_token_cost_flex": 5e-09, + "input_cost_per_token_above_272k_tokens_flex": 1e-07, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-07, + "output_cost_per_token_flex": 2.5e-07 + }, + "azure/gpt-6-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_priority": 4e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_priority": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -8464,28 +9360,39 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 5e-06, + "cache_read_input_token_cost_flex": 1e-07, + "cache_creation_input_token_cost_flex": 1.25e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06 }, - "azure/gpt-6-luna-2026-09-22": { - "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "azure/gpt-6-sol-2026-09-22": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_priority": 4e-07, "deprecation_date": "2028-03-11", - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_priority": 4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_272k_tokens": 7.5e-07, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -8513,33 +9420,35 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 5e-06, + "cache_read_input_token_cost_flex": 1e-07, + "cache_creation_input_token_cost_flex": 1.25e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06 }, - "azure/gpt-6-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, - "cache_creation_input_token_cost_priority": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, - "cache_read_input_token_cost_priority": 4e-07, - "deprecation_date": "2028-03-11", - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "input_cost_per_token_above_272k_tokens_priority": 8e-06, - "input_cost_per_token_priority": 4e-06, + "azure/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "output_cost_per_token_above_272k_tokens_priority": 3e-05, - "output_cost_per_token_priority": 2e-05, - "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, - "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8556,7 +9465,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8568,31 +9477,25 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, - "azure/gpt-6-sol-2026-09-22": { + "azure/gpt-terra-latest": { + "alias_of": "azure/gpt-6.1-terra" + }, + "azure/gpt-6.1-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, - "cache_creation_input_token_cost_priority": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, - "cache_read_input_token_cost_priority": 4e-07, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, "deprecation_date": "2028-03-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, - "input_cost_per_token_above_272k_tokens_priority": 8e-06, - "input_cost_per_token_priority": 4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, - "output_cost_per_token_above_272k_tokens_priority": 3e-05, - "output_cost_per_token_priority": 2e-05, - "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, - "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8609,7 +9512,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8619,9 +9522,20 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 5e-06, + "cache_read_input_token_cost_flex": 5e-08, + "cache_creation_input_token_cost_flex": 1.25e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06 }, - "azure/gpt-6.1-sol": { + "azure/gpt-sol-latest": { + "alias_of": "azure/gpt-6.1-sol" + }, + "azure/gpt-6.1-sol-2026-09-29": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_read_input_token_cost": 1e-07, @@ -8632,15 +9546,10 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", @@ -8658,7 +9567,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8668,29 +9577,35 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 5e-06, + "cache_read_input_token_cost_flex": 5e-08, + "cache_creation_input_token_cost_flex": 1.25e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06 }, - "azure/gpt-6.1-sol-2026-09-29": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "deprecation_date": "2028-03-11", - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, + "azure/us/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.375e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-06, + "cache_read_input_token_cost": 5.5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_above_272k_tokens": 2.2e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token": 5.5e-06, + "output_cost_per_token_above_272k_tokens": 8.25e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8707,7 +9622,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8730,14 +9645,13 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ @@ -8756,7 +9670,54 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/eu/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 3e-06, + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.2e-07, + "input_cost_per_token": 1.2e-06, + "input_cost_per_token_above_272k_tokens": 2.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_272k_tokens": 9e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8779,14 +9740,13 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ @@ -8805,7 +9765,54 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/apac/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 3e-06, + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.2e-07, + "input_cost_per_token": 1.2e-06, + "input_cost_per_token_above_272k_tokens": 2.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_272k_tokens": 9e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8828,14 +9835,13 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ @@ -8854,7 +9860,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8868,12 +9874,12 @@ }, "azure/gpt-chat-latest": { "cache_read_input_token_cost": 5e-07, - "deprecation_date": "2026-12-02", + "deprecation_date": "2027-05-18", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 5e-06, "litellm_provider": "azure", - "max_input_tokens": 272000, + "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "reasoning_effort_levels": [ @@ -8905,18 +9911,18 @@ }, "azure/chat-latest": { "cache_read_input_token_cost": 5e-07, - "deprecation_date": "2026-12-02", + "deprecation_date": "2027-05-18", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "reasoning_effort_levels": [ "medium" ], - "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8956,16 +9962,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9004,6 +10009,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, "cache_read_input_token_cost_priority": 8.8e-07, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-6-sol", "input_cost_per_token": 4.4e-06, "input_cost_per_token_above_272k_tokens": 8.8e-06, "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, @@ -9011,16 +10018,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9060,6 +10066,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07, "cache_read_input_token_cost_priority": 4.4e-07, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-6.1-terra", "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "input_cost_per_token_above_272k_tokens_priority": 8.8e-06, @@ -9067,16 +10075,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, "output_cost_per_token_above_272k_tokens_priority": 3.96e-05, "output_cost_per_token_priority": 2.64e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9116,6 +10123,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08, "cache_read_input_token_cost_priority": 4.4e-08, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-6-luna", "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, "input_cost_per_token_above_272k_tokens_priority": 8.8e-07, @@ -9123,16 +10132,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, "output_cost_per_token_above_272k_tokens_priority": 3.96e-06, "output_cost_per_token_priority": 2.64e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9173,14 +10181,13 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9199,7 +10206,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -9222,14 +10229,13 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-07, "output_cost_per_token_above_272k_tokens": 8.25e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ @@ -9277,13 +10283,12 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, "output_cost_per_token_above_272k_tokens_priority": 3.3e-05, "output_cost_per_token_priority": 2.2e-05, - "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -9315,12 +10320,12 @@ }, "azure/us/gpt-chat-latest": { "cache_read_input_token_cost": 5.5e-07, - "deprecation_date": "2026-12-02", + "deprecation_date": "2027-05-18", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "max_input_tokens": 272000, + "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.3e-05, "reasoning_effort_levels": [ @@ -9366,16 +10371,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9414,6 +10418,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, "cache_read_input_token_cost_priority": 8.8e-07, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-6-sol", "input_cost_per_token": 4.4e-06, "input_cost_per_token_above_272k_tokens": 8.8e-06, "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, @@ -9421,16 +10427,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9470,6 +10475,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07, "cache_read_input_token_cost_priority": 4.4e-07, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-6.1-terra", "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "input_cost_per_token_above_272k_tokens_priority": 8.8e-06, @@ -9477,16 +10484,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, "output_cost_per_token_above_272k_tokens_priority": 3.96e-05, "output_cost_per_token_priority": 2.64e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9526,6 +10532,8 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08, "cache_read_input_token_cost_priority": 4.4e-08, "deprecation_date": "2028-01-11", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-6-luna", "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, "input_cost_per_token_above_272k_tokens_priority": 8.8e-07, @@ -9533,16 +10541,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, "output_cost_per_token_above_272k_tokens_priority": 3.96e-06, "output_cost_per_token_priority": 2.64e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9574,6 +10581,8 @@ }, "azure/gpt-5.5": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, @@ -9592,7 +10601,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, @@ -9601,9 +10609,9 @@ "output_cost_per_token_above_272k_tokens_priority": 9e-05, "output_cost_per_token_batches": 1.5e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9635,6 +10643,8 @@ }, "azure/us/gpt-5.5": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, @@ -9651,14 +10661,13 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9690,6 +10699,8 @@ }, "azure/eu/gpt-5.5": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, @@ -9706,14 +10717,13 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -9758,16 +10768,15 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9793,6 +10802,8 @@ "supports_vision": true, "supports_web_search": true, "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6", "input_cost_per_token_above_272k_tokens_batches": 5e-06, "input_cost_per_token_above_272k_tokens_flex": 5e-06, "input_cost_per_token_batches": 2.5e-06, @@ -9803,6 +10814,8 @@ }, "azure/gpt-5.5-2026-04-24": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1.25e-06, @@ -9818,7 +10831,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_batches": 1.5e-05, @@ -9826,9 +10838,9 @@ "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9877,12 +10889,11 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9908,6 +10919,8 @@ "supports_vision": true, "supports_web_search": true, "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6", "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, @@ -9916,6 +10929,8 @@ }, "azure/us/gpt-5.5-2026-04-24": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_priority": 1.375e-06, @@ -9930,12 +10945,11 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -9984,12 +10998,11 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10015,6 +11028,8 @@ "supports_vision": true, "supports_web_search": true, "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6", "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, @@ -10023,6 +11038,8 @@ }, "azure/eu/gpt-5.5-2026-04-24": { "deprecation_date": "2027-10-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_priority": 1.375e-06, @@ -10037,12 +11054,11 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10084,14 +11100,13 @@ "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/batch", @@ -10128,14 +11143,13 @@ "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/batch", @@ -10162,6 +11176,7 @@ }, "azure/gpt-5.4-mini": { "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, @@ -10170,13 +11185,12 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10212,22 +11226,25 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, + "azure/gpt-mini-latest": { + "alias_of": "azure/gpt-5.4-mini" + }, "azure/gpt-5.4-mini-2026-03-17": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_flex": 3.75e-08, "cache_read_input_token_cost_priority": 1.5e-07, "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 7.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10266,6 +11283,7 @@ }, "azure/gpt-5.4-nano": { "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_flex": 1e-08, @@ -10273,13 +11291,12 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10317,17 +11334,17 @@ "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", @@ -10366,6 +11383,8 @@ "cache_read_input_image_token_cost": 2.5e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-image-1.5", "input_cost_per_image_token": 1e-05, "input_cost_per_token": 5e-06, "litellm_provider": "azure", @@ -10400,6 +11419,7 @@ }, "azure/high/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.59263611e-07, "litellm_provider": "azure", "mode": "image_generation", @@ -10410,6 +11430,7 @@ }, "azure/high/1024-x-1536/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "azure", "mode": "image_generation", @@ -10420,6 +11441,7 @@ }, "azure/high/1536-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "azure", "mode": "image_generation", @@ -10430,6 +11452,7 @@ }, "azure/low/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.0490417e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10440,6 +11463,7 @@ }, "azure/low/1024-x-1536/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10450,6 +11474,7 @@ }, "azure/low/1536-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10460,6 +11485,7 @@ }, "azure/medium/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10470,6 +11496,7 @@ }, "azure/medium/1024-x-1536/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10480,6 +11507,7 @@ }, "azure/medium/1536-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10492,6 +11520,7 @@ "cache_read_input_image_token_cost": 2.5e-07, "cache_read_input_token_cost": 2e-07, "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_image_token": 2.5e-06, "input_cost_per_token": 2e-06, "litellm_provider": "azure", @@ -10506,6 +11535,8 @@ "azure/gpt-image-1.5": { "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2026-12-16", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-image-2", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, @@ -10523,6 +11554,8 @@ "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-12-16", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-image-2", "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", @@ -10538,6 +11571,7 @@ "azure/gpt-image-2": { "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-10-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, @@ -10555,6 +11589,7 @@ "azure/gpt-image-2.5-flare": { "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-09-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, @@ -10572,6 +11607,7 @@ "azure/gpt-image-2.5-sunburst": { "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-09-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, @@ -10590,6 +11626,7 @@ "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-10-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", @@ -10605,6 +11642,7 @@ }, "azure/low/1024-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 2.0751953125e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -10615,6 +11653,7 @@ }, "azure/low/1024-x-1536/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 2.0751953125e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -10625,6 +11664,7 @@ }, "azure/low/1536-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 2.0345052083e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -10635,6 +11675,7 @@ }, "azure/medium/1024-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 8.056640625e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -10645,6 +11686,7 @@ }, "azure/medium/1024-x-1536/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 8.056640625e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -10655,6 +11697,7 @@ }, "azure/medium/1536-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 7.9752604167e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -10665,6 +11708,7 @@ }, "azure/high/1024-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 3.173828125e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10675,6 +11719,7 @@ }, "azure/high/1024-x-1536/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 3.173828125e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10685,6 +11730,7 @@ }, "azure/high/1536-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 3.1575520833e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -10697,7 +11743,7 @@ "input_cost_per_token": 8e-06, "litellm_provider": "azure", "max_input_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_function_calling": true @@ -10706,19 +11752,19 @@ "input_cost_per_token": 8e-06, "litellm_provider": "azure", "max_input_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_function_calling": true }, "azure/o1": { "deprecation_date": "2026-11-19", + "successor_model": "azure/gpt-5.6-sol", "cache_read_input_token_cost": 7.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_function_calling": true, @@ -10731,12 +11777,12 @@ "azure/o1-2024-12-17": { "cache_read_input_token_cost": 7.5e-06, "deprecation_date": "2026-11-19", + "successor_model": "azure/gpt-5.6-sol", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_batches": 3e-05, @@ -10755,7 +11801,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -10773,7 +11818,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -10786,14 +11830,22 @@ }, "azure/o3": { "deprecation_date": "2026-11-19", + "successor_model": "azure/gpt-5.6-sol", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -10816,16 +11868,21 @@ }, "azure/o3-2025-04-16": { "deprecation_date": "2026-11-19", + "successor_model": "azure/gpt-5.6-sol", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -10850,21 +11907,21 @@ "azure/o3-deep-research": { "cache_read_input_token_cost": 2.5e-06, "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6-sol", "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 4e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ - "/v1/chat/completions", "/v1/batch", "/v1/responses" ], @@ -10888,14 +11945,18 @@ }, "azure/o3-mini": { "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6-terra", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -10905,12 +11966,13 @@ "azure/o3-mini-2025-01-31": { "cache_read_input_token_cost": 5.5e-07, "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6-terra", "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -10922,18 +11984,23 @@ }, "azure/o3-pro": { "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6-sol", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ - "/v1/chat/completions", "/v1/batch", "/v1/responses" ], @@ -10954,18 +12021,23 @@ }, "azure/o3-pro-2025-06-10": { "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6-sol", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ - "/v1/chat/completions", "/v1/batch", "/v1/responses" ], @@ -10986,14 +12058,23 @@ }, "azure/o4-mini": { "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6-terra", "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -11017,15 +12098,21 @@ "azure/o4-mini-2025-04-16": { "cache_read_input_token_cost": 2.75e-07, "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-5.6-terra", "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, @@ -11064,33 +12151,33 @@ }, "azure/text-embedding-3-large": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 1.3e-07, + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-3-small": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 2e-08, + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-ada-002": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 1e-07, + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/speech/azure-tts": { "input_cost_per_character": 1.5e-05, @@ -11117,18 +12204,24 @@ }, "azure/tts-1": { "deprecation_date": "2026-12-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_character": 1.5e-05, "litellm_provider": "azure", - "mode": "audio_speech" + "mode": "audio_speech", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure/tts-1-hd": { "deprecation_date": "2026-12-15", - "input_cost_per_character": 3e-05, + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_character": 3.3e-05, "litellm_provider": "azure", - "mode": "audio_speech" + "mode": "audio_speech", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure/us/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_priority": 9.63e-07, "input_cost_per_token": 2.2e-06, @@ -11137,11 +12230,15 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11167,6 +12264,8 @@ }, "azure/us/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-mini", "cache_read_input_token_cost": 1.1e-07, "cache_read_input_token_cost_priority": 1.93e-07, "input_cost_per_token": 4.4e-07, @@ -11175,11 +12274,15 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11205,13 +12308,14 @@ }, "azure/us/gpt-4.1-nano-2025-04-14": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-nano", "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 5.5e-08, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, @@ -11239,13 +12343,14 @@ }, "azure/us/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -11257,8 +12362,31 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/gpt-4o": { + "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", + "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, + "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", "cache_creation_input_token_cost": 1.38e-06, "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, @@ -11266,7 +12394,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -11277,17 +12404,46 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/gpt-4o-mini": { + "cache_read_input_token_cost": 8.3e-08, + "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.65e-07, "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -11304,7 +12460,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2.2e-05, "output_cost_per_token": 2.64e-06, @@ -11315,40 +12470,18 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "azure/us/gpt-4o-realtime-preview-2024-10-01": { - "cache_creation_input_audio_token_cost": 2.2e-05, - "cache_read_input_token_cost": 2.75e-06, - "deprecation_date": "2025-03-26", - "input_cost_per_audio_token": 0.00011, - "input_cost_per_token": 5.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 0.00022, - "output_cost_per_token": 2.2e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "azure/us/gpt-4o-realtime-preview-2024-12-17": { - "cache_read_input_audio_token_cost": 2.5e-06, + "cache_read_input_audio_token_cost": 2.75e-06, "cache_read_input_token_cost": 2.75e-06, "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" @@ -11368,17 +12501,23 @@ "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_priority": 2.75e-07, "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", "input_cost_per_token": 1.375e-06, "input_cost_per_token_batches": 6.875e-07, "input_cost_per_token_priority": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11407,18 +12546,24 @@ "azure/us/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, "cache_read_input_token_cost_priority": 4.95e-08, - "deprecation_date": "2027-02-09", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-mini", "input_cost_per_token": 2.75e-07, "input_cost_per_token_batches": 1.375e-07, "input_cost_per_token_priority": 4.95e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11447,15 +12592,21 @@ "azure/us/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5.5e-09, "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-nano", "input_cost_per_token": 5.5e-08, "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11482,7 +12633,9 @@ "cache_read_input_token_cost_batches": 2.75e-09 }, "azure/us/gpt-5.1": { - "deprecation_date": "2027-05-15", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.2", "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_batches": 6.875e-08, "cache_read_input_token_cost_priority": 2.75e-07, @@ -11490,7 +12643,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ @@ -11522,16 +12674,22 @@ "input_cost_per_token_priority": 2.75e-06, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.2-codex", "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11558,12 +12716,12 @@ }, "azure/us/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11588,15 +12746,34 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/o1": { + "cache_read_input_token_cost": 8.25e-06, + "deprecation_date": "2026-11-19", + "successor_model": "azure/us/gpt-5.6-sol", + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", + "successor_model": "azure/us/gpt-5.6-sol", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, "output_cost_per_token_batches": 3.3e-05, @@ -11614,7 +12791,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, @@ -11624,18 +12800,61 @@ "supports_prompt_caching": true, "supports_vision": false }, + "azure/us/o3": { + "deprecation_date": "2026-11-19", + "successor_model": "azure/us/gpt-5.6-sol", + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/o3-2025-04-16": { "deprecation_date": "2026-11-19", + "successor_model": "azure/us/gpt-5.6-sol", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", @@ -11657,15 +12876,35 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/o3-mini": { + "cache_read_input_token_cost": 6.05e-07, + "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6-terra", + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "azure/us/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6-terra", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, @@ -11675,18 +12914,51 @@ "supports_tool_choice": true, "supports_vision": false }, + "azure/us/o4-mini": { + "cache_read_input_token_cost": 3.03e-07, + "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6-terra", + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/o4-mini-2025-04-16": { "cache_read_input_token_cost": 3.03e-07, "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6-terra", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, @@ -11697,17 +12969,21 @@ "supports_vision": true }, "azure/whisper-1": { - "deprecation_date": "2026-12-15", + "deprecation_date": "2027-02-26", + "deprecation_source": "https://management.azure.com/subscriptions/a88257a5-3323-4ef9-95bf-5681a46c9624/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", "input_cost_per_second": 0.0001, "litellm_provider": "azure", "mode": "audio_transcription", - "output_cost_per_second": 0.0001 + "output_cost_per_second": 0.0001, + "source": "https://management.azure.com/subscriptions/a88257a5-3323-4ef9-95bf-5681a46c9624/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01" }, "azure_ai/Cohere-embed-v3-english": { + "deprecation_date": "2027-02-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/Cohere-Embed-V5-Fast", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -11715,10 +12991,12 @@ "supports_embedding_image_input": true }, "azure_ai/Cohere-embed-v3-multilingual": { + "deprecation_date": "2027-02-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/Cohere-Embed-V5-Fast", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -11726,11 +13004,12 @@ "supports_embedding_image_input": true }, "azure_ai/Codestral-2501": { + "deprecation_date": "2027-02-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11743,12 +13022,14 @@ "supported_output_modalities": [ "text" ], - "supports_native_streaming": true + "supports_native_streaming": true, + "supports_pdf_input": false }, "azure_ai/FLUX-1.1-pro": { + "deprecation_date": "2027-01-05", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", "max_input_tokens": 5000, - "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", @@ -11757,9 +13038,10 @@ ] }, "azure_ai/FLUX.1-Kontext-pro": { + "deprecation_date": "2027-01-05", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", "max_input_tokens": 5000, - "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/", @@ -11768,9 +13050,10 @@ ] }, "azure_ai/flux.2-pro": { + "deprecation_date": "2027-01-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -11779,10 +13062,11 @@ ] }, "azure_ai/FLUX.2-flex": { + "deprecation_date": "2027-01-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_pixel": 5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "image_generation", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/", "supported_endpoints": [ @@ -11804,11 +13088,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -11819,43 +13103,45 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.828e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-GLM-5": { "deprecation_date": "2027-07-01", + "successor_model": "azure_ai/FW-GLM-5.2", "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.52e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-GLM-5.1": { "deprecation_date": "2027-07-01", + "successor_model": "azure_ai/FW-GLM-5.2", "cache_read_input_token_cost": 2.86e-07, "input_cost_per_token": 1.54e-06, "litellm_provider": "azure_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -11866,11 +13152,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -11881,11 +13167,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 7.26e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -11896,7 +13182,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.46e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11907,6 +13192,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -11918,7 +13204,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.3e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11930,6 +13215,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -11941,7 +13227,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11953,6 +13238,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -11964,7 +13250,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11976,6 +13261,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -11987,7 +13273,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ @@ -12004,11 +13289,15 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, + "azure_ai/kimi-latest": { + "alias_of": "azure_ai/FW-Kimi-K3" + }, "azure_ai/FW-MiniMax-M2.5": { "deprecation_date": "2027-07-01", "cache_read_input_token_cost": 3.3e-08, @@ -12016,11 +13305,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -12031,7 +13320,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12043,11 +13331,15 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, + "azure_ai/minimax-latest": { + "alias_of": "azure_ai/FW-MiniMax-M3" + }, "azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 6e-08, @@ -12063,6 +13355,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -12074,7 +13367,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.64e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12085,6 +13377,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -12102,6 +13395,8 @@ "/v1/images/edits" ], "deprecation_date": "2026-10-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/MAI-Image-2.6", "max_input_tokens": 32000 }, "azure_ai/MAI-Image-2.5-Flash": { @@ -12117,10 +13412,13 @@ "/v1/images/edits" ], "deprecation_date": "2026-10-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/MAI-Image-2.6-Flash", "max_input_tokens": 32000 }, "azure_ai/MAI-Image-2.5-Pro": { "deprecation_date": "2026-10-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", @@ -12140,7 +13438,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12154,259 +13451,143 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/Llama-3.3-70B-Instruct": { + "deprecation_date": "2027-01-31", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 7.1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.1e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/Llama-4-Scout-17B-16E-Instruct": { + "deprecation_date": "2027-01-31", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 10000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure_ai/Meta-Llama-3-70B-Instruct": { - "deprecation_date": "2025-06-30", - "input_cost_per_token": 1.1e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 3.7e-07, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_tool_choice": true - }, - "azure_ai/Meta-Llama-3.1-70B-Instruct": { - "deprecation_date": "2025-06-30", - "input_cost_per_token": 2.68e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 3.54e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_tool_choice": true - }, - "azure_ai/Phi-3-medium-128k-instruct": { - "deprecation_date": "2025-08-30", - "input_cost_per_token": 1.7e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6.8e-07, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3-medium-4k-instruct": { - "deprecation_date": "2025-08-30", - "input_cost_per_token": 1.7e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6.8e-07, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3-mini-128k-instruct": { - "deprecation_date": "2025-08-30", - "input_cost_per_token": 1.3e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 5.2e-07, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3-mini-4k-instruct": { - "deprecation_date": "2025-08-30", - "input_cost_per_token": 1.3e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 5.2e-07, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3-small-128k-instruct": { - "deprecation_date": "2025-08-30", - "input_cost_per_token": 1.5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3-small-8k-instruct": { - "deprecation_date": "2025-08-30", - "input_cost_per_token": 1.5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3.5-MoE-instruct": { - "deprecation_date": "2025-08-30", - "input_cost_per_token": 1.6e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6.4e-07, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3.5-mini-instruct": { - "deprecation_date": "2025-08-30", - "input_cost_per_token": 1.3e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 5.2e-07, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_tool_choice": true, - "supports_vision": false - }, - "azure_ai/Phi-3.5-vision-instruct": { - "deprecation_date": "2025-08-30", - "input_cost_per_token": 1.3e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 5.2e-07, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", + "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/Phi-4": { + "deprecation_date": "2027-01-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "microsoft--phi-4", "input_cost_per_token": 1.25e-07, "litellm_provider": "azure_ai", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-4-mini-instruct": { + "deprecation_date": "2027-01-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "microsoft--phi-4", "input_cost_per_token": 7.5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true + "supports_function_calling": true, + "supports_pdf_input": false }, "azure_ai/Phi-4-multimodal-instruct": { + "deprecation_date": "2027-01-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "microsoft--phi-4", "input_cost_per_audio_token": 4e-06, "input_cost_per_token": 8e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_audio_input": true, "supports_function_calling": true, + "supports_pdf_input": false, "supports_vision": true }, "azure_ai/Phi-4-mini-reasoning": { + "deprecation_date": "2027-01-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "microsoft--phi-4", "input_cost_per_token": 7.5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_function_calling": true + "supports_function_calling": true, + "supports_pdf_input": false }, "azure_ai/Phi-4-reasoning": { + "deprecation_date": "2027-01-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "microsoft--phi-4", "input_cost_per_token": 1.25e-07, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true }, "azure_ai/mistral-document-ai-2512": { + "deprecation_date": "2027-02-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.003, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" ], - "source": "https://ai.azure.com/catalog/models/mistral-document-ai-2512" + "source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/mistral-ocr-4-0" }, "azure_ai/mistral-ocr-4-0": { "litellm_provider": "azure_ai", @@ -12420,6 +13601,7 @@ }, "azure_ai/Cohere-parse-v5": { "deprecation_date": "2026-12-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", "mode": "ocr", "ocr_cost_per_page": 0.0015, @@ -12429,15 +13611,18 @@ ] }, "azure_ai/cohere-command-a": { + "deprecation_date": "2027-02-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "coherelabs-command-a-plus-05-2026-fp81", "input_cost_per_token": 2.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 8182, - "max_tokens": 8182, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/doc-intelligence/prebuilt-read": { @@ -12469,158 +13654,145 @@ }, "azure_ai/MAI-DS-R1": { "deprecation_date": "2026-02-27", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "input_cost_per_token": 1.35e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", + "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true }, - "azure_ai/cohere-rerank-v3-english": { - "deprecation_date": "2025-06-30", - "input_cost_per_query": 0.002, - "input_cost_per_token": 0.0, - "litellm_provider": "azure_ai", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "rerank", - "output_cost_per_token": 0.0, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" - }, - "azure_ai/cohere-rerank-v3-multilingual": { - "deprecation_date": "2025-06-30", - "input_cost_per_query": 0.002, - "input_cost_per_token": 0.0, - "litellm_provider": "azure_ai", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "rerank", - "output_cost_per_token": 0.0, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" - }, "azure_ai/cohere-rerank-v4.0-pro": { + "deprecation_date": "2027-09-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/cohere-rerank-v5-pro", "input_cost_per_query": 0.0025, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" }, "azure_ai/cohere-rerank-v4.0-fast": { + "deprecation_date": "2027-09-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/cohere-rerank-v5-fast", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" }, "azure_ai/deepseek-v3.2": { + "deprecation_date": "2027-11-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/deepseek-v4.1-flash", "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/deepseek-v3.2-speciale": { + "deprecation_date": "2027-11-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/deepseek-v4-pro", "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, - "azure_ai/deepseek-v3": { - "deprecation_date": "2025-08-31", - "input_cost_per_token": 1.14e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4.56e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_tool_choice": true - }, "azure_ai/deepseek-v4-pro": { "deprecation_date": "2028-02-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.74e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true, "cache_read_input_token_cost": 1.45e-07, "supports_prompt_caching": true }, + "azure_ai/deepseek-pro-latest": { + "alias_of": "azure_ai/deepseek-v4-pro" + }, "azure_ai/deepseek-v4-flash": { "deprecation_date": "2028-02-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/DeepSeek-V4-Flash-0731", "input_cost_per_token": 1.9e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 5.1e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true, "cache_read_input_token_cost": 2.8e-08, "supports_prompt_caching": true }, + "azure_ai/deepseek-flash-latest": { + "alias_of": "azure_ai/deepseek-v4-flash" + }, "azure_ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 1.4e-08, "deprecation_date": "2026-12-03", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 4.4e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/embed-v-4-0": { + "deprecation_date": "2027-06-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/Cohere-Embed-V5-Fast", "input_cost_per_token": 1.2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 3072, @@ -12636,15 +13808,18 @@ "input_cost_per_image_token": 4.7e-07 }, "azure_ai/grok-4": { + "deprecation_date": "2027-01-31", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/grok-4.3", "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, + "supports_pdf_input": false, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true @@ -12657,12 +13832,12 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -12678,12 +13853,12 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -12694,15 +13869,16 @@ "azure_ai/grok-4-20-reasoning": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-06", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -12713,15 +13889,16 @@ "azure_ai/grok-4-20-non-reasoning": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-06", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -12729,82 +13906,82 @@ "supports_web_search": true }, "azure_ai/grok-4-1-fast-non-reasoning": { + "deprecation_date": "2027-05-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/grok-4-1-fast-reasoning": { + "deprecation_date": "2027-05-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", + "token_count_framing": 149, + "token_count_tool_framing": 302, + "token_count_responses_framing": 145, + "token_count_responses_tool_framing": 100, "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/grok-code-fast-1": { + "deprecation_date": "2027-01-31", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, + "supports_pdf_input": false, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/jais-30b-chat": { "deprecation_date": "2026-01-30", - "input_cost_per_token": 0.0032, + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", + "input_cost_per_token": 3.2e-06, "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00971, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" - }, - "azure_ai/jamba-instruct": { - "deprecation_date": "2025-03-01", - "input_cost_per_token": 5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 70000, - "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 7e-07, + "output_cost_per_token": 9.71e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_tool_choice": true + "supports_pdf_input": false }, "azure_ai/kimi-k2.5": { "deprecation_date": "2027-01-26", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, @@ -12813,11 +13990,11 @@ }, "azure_ai/kimi-k2.6": { "deprecation_date": "2027-04-16", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 9.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12829,6 +14006,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, @@ -12836,41 +14014,18 @@ "supports_prompt_caching": true }, "azure_ai/ministral-3b": { + "deprecation_date": "2026-12-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "ministral-ministral-4b-instruct", "input_cost_per_token": 4e-08, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-08, "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure_ai/mistral-large": { - "deprecation_date": "2025-04-15", - "input_cost_per_token": 4e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure_ai/mistral-large-2407": { - "deprecation_date": "2025-05-13", - "input_cost_per_token": 2e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/mistral-large-latest": { @@ -12878,11 +14033,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/mistral-large-3": { @@ -12890,71 +14045,67 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/mistral-medium-2505": { + "deprecation_date": "2026-12-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/mistral-medium-3-5", "input_cost_per_token": 4e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/mistral-nemo": { "deprecation_date": "2026-01-30", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", + "successor_model": "azure_ai/mistral-small-2503", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", - "supports_function_calling": true - }, - "azure_ai/mistral-small": { - "deprecation_date": "2025-07-31", - "input_cost_per_token": 1e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true, - "supports_tool_choice": true + "supports_pdf_input": false }, "azure_ai/mistral-small-2503": { + "deprecation_date": "2027-02-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "mistralai-mistral-small-4-119b-2603", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": true }, "babbage-002": { "deprecation_date": "2026-09-28", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -12966,7 +14117,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -12976,7 +14126,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -12986,7 +14135,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -12996,7 +14144,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -13021,7 +14168,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13031,7 +14177,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { @@ -13040,7 +14185,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13050,7 +14194,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13060,7 +14203,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { @@ -13069,7 +14211,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13078,7 +14219,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 7.55e-06, "supports_tool_choice": true @@ -13088,7 +14228,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -13098,21 +14237,23 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/ap-northeast-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_batches": 3.7e-07, "input_cost_per_token_flex": 3.7e-07, + "input_cost_per_token_priority": 1.295e-06, "litellm_provider": "bedrock", - "max_input_tokens": 163840, + "max_input_tokens": 156000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_batches": 1.11e-06, "output_cost_per_token_flex": 1.11e-06, + "output_cost_per_token_priority": 3.885e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13120,36 +14261,41 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/ap-northeast-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/ap-northeast-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13158,16 +14304,18 @@ "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.44e-06, - "output_cost_per_token_flex": 7.2e-07 + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06 }, "bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 7.3e-07, "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.03e-06, "output_cost_per_token_flex": 1.52e-06, @@ -13177,21 +14325,24 @@ }, "bedrock/ap-northeast-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "input_cost_per_token_flex": 3.6e-07, + "input_cost_per_token_priority": 1.26e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_batches": 1.8e-06, "output_cost_per_token_flex": 1.8e-06, + "output_cost_per_token_priority": 6.3e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/ap-northeast-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, @@ -13199,26 +14350,25 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" + "supports_vision": false }, "bedrock/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_flex": 1.25e-06, @@ -13229,13 +14379,14 @@ "bedrock/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.25e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_reasoning": true, @@ -13248,36 +14399,39 @@ }, "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 3.18e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/ap-south-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_batches": 3.7e-07, "input_cost_per_token_flex": 3.7e-07, + "input_cost_per_token_priority": 1.295e-06, "litellm_provider": "bedrock", - "max_input_tokens": 163840, + "max_input_tokens": 156000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_batches": 1.11e-06, "output_cost_per_token_flex": 1.11e-06, + "output_cost_per_token_priority": 3.885e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13285,36 +14439,41 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/ap-south-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/ap-south-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13323,16 +14482,18 @@ "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.44e-06, - "output_cost_per_token_flex": 7.2e-07 + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06 }, "bedrock/ap-south-1/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 7.1e-07, "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.94e-06, "output_cost_per_token_flex": 1.47e-06, @@ -13342,21 +14503,24 @@ }, "bedrock/ap-south-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "input_cost_per_token_flex": 3.6e-07, + "input_cost_per_token_priority": 1.26e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_batches": 1.8e-06, "output_cost_per_token_flex": 1.8e-06, + "output_cost_per_token_priority": 6.3e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/ap-south-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, @@ -13364,27 +14528,27 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" + "supports_vision": false }, "bedrock/ap-southeast-2/minimax.minimax-m2.5": { "input_cost_per_token": 3.1e-07, + "input_cost_per_token_batches": 1.55e-07, "input_cost_per_token_flex": 1.55e-07, + "input_cost_per_token_priority": 5.425e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13393,45 +14557,46 @@ "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.24e-06, - "output_cost_per_token_flex": 6.2e-07 + "output_cost_per_token_batches": 6.2e-07, + "output_cost_per_token_flex": 6.2e-07, + "output_cost_per_token_priority": 2.17e-06 }, "bedrock/ap-southeast-3/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock", - "max_input_tokens": 163840, + "max_input_tokens": 156000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, "output_cost_per_token_flex": 1.11e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md", + "supports_audio_input": false, "supports_function_calling": true, - "supports_reasoning": true, "supports_native_structured_output": true, - "supports_tool_choice": true, - "supports_audio_input": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" + "supports_tool_choice": true, + "supports_vision": false }, "bedrock/ap-southeast-3/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html", "input_cost_per_token": 3.6e-07, "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" + "supports_vision": false }, "bedrock/ap-southeast-3/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, @@ -13439,18 +14604,17 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", + "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "output_cost_per_token": 1.44e-06, - "output_cost_per_token_flex": 7.2e-07 + "supports_vision": false }, "bedrock/ap-southeast-3/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, @@ -13458,17 +14622,16 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, "output_cost_per_token_flex": 1.8e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_audio_input": false, - "supports_response_schema": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" + "supports_vision": true }, "bedrock/ap-southeast-3/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, @@ -13476,50 +14639,52 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" + "supports_vision": false }, "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 3.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.03e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.9e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-north-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_batches": 3.7e-07, "input_cost_per_token_flex": 3.7e-07, + "input_cost_per_token_priority": 1.295e-06, "litellm_provider": "bedrock", - "max_input_tokens": 163840, + "max_input_tokens": 156000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_batches": 1.11e-06, "output_cost_per_token_flex": 1.11e-06, + "output_cost_per_token_priority": 3.885e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13527,36 +14692,41 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/eu-north-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-north-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13565,25 +14735,30 @@ "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.44e-06, - "output_cost_per_token_flex": 7.2e-07 + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06 }, "bedrock/eu-north-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "input_cost_per_token_flex": 3.6e-07, + "input_cost_per_token_priority": 1.26e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_batches": 1.8e-06, "output_cost_per_token_flex": 1.8e-06, + "output_cost_per_token_priority": 6.3e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { "cost_per_second": 0.01635, @@ -13591,7 +14766,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13601,7 +14775,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { @@ -13610,7 +14783,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13620,7 +14792,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13630,7 +14801,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { @@ -13639,7 +14809,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13648,7 +14817,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 8.38e-06, "supports_tool_choice": true @@ -13658,7 +14826,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05 }, @@ -13667,39 +14834,43 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/eu-central-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-central-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13708,7 +14879,9 @@ "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.44e-06, - "output_cost_per_token_flex": 7.2e-07 + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06 }, "bedrock/eu-central-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, @@ -13716,68 +14889,72 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" + "supports_vision": false }, "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 2.86e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.78e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.5e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-west-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-west-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13786,7 +14963,9 @@ "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.44e-06, - "output_cost_per_token_flex": 7.2e-07 + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06 }, "bedrock/eu-west-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, @@ -13794,68 +14973,72 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" + "supports_vision": false }, "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 3.45e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.55e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-west-2/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 4.7e-07, + "input_cost_per_token_batches": 2.35e-07, "input_cost_per_token_flex": 2.35e-07, + "input_cost_per_token_priority": 8.225e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.86e-06, + "output_cost_per_token_batches": 9.3e-07, "output_cost_per_token_flex": 9.3e-07, + "output_cost_per_token_priority": 3.255e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-west-2/minimax.minimax-m2.5": { "input_cost_per_token": 4.7e-07, + "input_cost_per_token_batches": 2.35e-07, "input_cost_per_token_flex": 2.35e-07, + "input_cost_per_token_priority": 8.225e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13864,19 +15047,24 @@ "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.86e-06, - "output_cost_per_token_flex": 9.3e-07 + "output_cost_per_token_batches": 9.3e-07, + "output_cost_per_token_flex": 9.3e-07, + "output_cost_per_token_priority": 3.255e-06 }, "bedrock/eu-west-2/nvidia.nemotron-super-3-120b": { "input_cost_per_token": 2.3e-07, + "input_cost_per_token_batches": 1.15e-07, "input_cost_per_token_flex": 1.15e-07, + "input_cost_per_token_priority": 4.025e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.01e-06, + "output_cost_per_token_batches": 5.05e-07, "output_cost_per_token_flex": 5.05e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_priority": 1.7675e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, @@ -13887,29 +15075,32 @@ }, "bedrock/eu-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 7.8e-07, + "input_cost_per_token_batches": 3.9e-07, "input_cost_per_token_flex": 3.9e-07, + "input_cost_per_token_priority": 1.365e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.86e-06, + "output_cost_per_token_batches": 9.3e-07, "output_cost_per_token_flex": 9.3e-07, + "output_cost_per_token_priority": 3.255e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", @@ -13920,7 +15111,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.56e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", @@ -13928,11 +15118,11 @@ }, "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "input_cost_per_token": 5.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9.1e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", @@ -13940,22 +15130,22 @@ }, "bedrock/eu-south-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html", "input_cost_per_token": 3.6e-07, "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" + "supports_vision": false }, "bedrock/eu-south-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, @@ -13963,18 +15153,17 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", + "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "output_cost_per_token": 1.44e-06, - "output_cost_per_token_flex": 7.2e-07 + "supports_vision": false }, "bedrock/eu-south-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, @@ -13982,24 +15171,22 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" + "supports_vision": false }, "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Anthropic via Invoke route does not currently support pdf input." }, @@ -14014,36 +15201,39 @@ }, "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 4.45e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.88e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.01e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/sa-east-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_batches": 3.7e-07, "input_cost_per_token_flex": 3.7e-07, + "input_cost_per_token_priority": 1.295e-06, "litellm_provider": "bedrock", - "max_input_tokens": 163840, + "max_input_tokens": 156000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_batches": 1.11e-06, "output_cost_per_token_flex": 1.11e-06, + "output_cost_per_token_priority": 3.885e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -14051,36 +15241,41 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/sa-east-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/sa-east-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, + "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -14089,16 +15284,18 @@ "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.44e-06, - "output_cost_per_token_flex": 7.2e-07 + "output_cost_per_token_batches": 7.2e-07, + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.52e-06 }, "bedrock/sa-east-1/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 7.3e-07, "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.03e-06, "output_cost_per_token_flex": 1.52e-06, @@ -14108,21 +15305,24 @@ }, "bedrock/sa-east-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "input_cost_per_token_flex": 3.6e-07, + "input_cost_per_token_priority": 1.26e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_batches": 1.8e-06, "output_cost_per_token_flex": 1.8e-06, + "output_cost_per_token_priority": 6.3e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/sa-east-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, @@ -14130,17 +15330,16 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" + "supports_vision": false }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { "cost_per_second": 0.011, @@ -14148,7 +15347,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14158,7 +15356,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { @@ -14167,7 +15364,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14177,7 +15373,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14187,7 +15382,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { @@ -14196,7 +15390,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14205,7 +15398,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true @@ -14215,7 +15407,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -14225,40 +15416,39 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", @@ -14269,7 +15459,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", @@ -14277,11 +15466,11 @@ }, "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", @@ -14289,14 +15478,17 @@ }, "bedrock/us-east-1/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_batches": 3.1e-07, "input_cost_per_token_flex": 3.1e-07, + "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock", - "max_input_tokens": 163840, + "max_input_tokens": 156000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_batches": 9.25e-07, "output_cost_per_token_flex": 9.25e-07, + "output_cost_per_token_priority": 3.2375e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -14304,53 +15496,60 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/us-east-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-1/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-1/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_flex": 1.25e-06, @@ -14360,50 +15559,59 @@ }, "bedrock/us-east-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.25e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-1/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 8.75e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-2/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_batches": 3.1e-07, "input_cost_per_token_flex": 3.1e-07, + "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock", - "max_input_tokens": 163840, + "max_input_tokens": 156000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_batches": 9.25e-07, "output_cost_per_token_flex": 9.25e-07, + "output_cost_per_token_priority": 3.2375e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -14411,36 +15619,41 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/us-east-2/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-2/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -14449,16 +15662,18 @@ "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.2e-06, - "output_cost_per_token_flex": 6e-07 + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06 }, "bedrock/us-east-2/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_flex": 1.25e-06, @@ -14468,21 +15683,24 @@ }, "bedrock/us-east-2/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.25e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-2/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, @@ -14490,17 +15708,16 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" + "supports_vision": false }, "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.4e-07, @@ -14508,7 +15725,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.84e-06, "supports_function_calling": true, @@ -14522,16 +15738,14 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 }, "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0": { - "input_cost_per_token": 2e-07, + "input_cost_per_token": 3e-08, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -14541,7 +15755,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.7e-06 }, @@ -14550,7 +15763,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-07 }, @@ -14559,7 +15771,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, @@ -14567,12 +15778,14 @@ "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-27", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14586,18 +15799,24 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-27", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14611,14 +15830,15 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", + "token_count_model": {"model":"anthropic.claude-sonnet-4-5-20250929-v1:0","litellm_provider":"bedrock"} }, "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.5e-06, "supports_pdf_input": true @@ -14628,7 +15848,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 2.65e-06, "supports_pdf_input": true @@ -14636,14 +15855,15 @@ "bedrock/us-gov-west-1/amazon.nova-2-multimodal-embeddings-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 8172, - "max_tokens": 8172, "mode": "embedding", "input_cost_per_token": 1.62e-07, "input_cost_per_image": 7.2e-05, "input_cost_per_video_per_second": 0.00084, "input_cost_per_audio_per_second": 0.000168, + "input_cost_per_token_batches": 8.1e-08, "output_cost_per_token": 0.0, "output_vector_size": 3072, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_embedding_image_input": true, "supports_image_input": true, "supports_video_input": true, @@ -14652,12 +15872,14 @@ "bedrock/us-gov-west-1/amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.8e-08, "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.88e-07, + "output_cost_per_token_batches": 1.44e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -14668,12 +15890,14 @@ "bedrock/us-gov-west-1/amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 1.05e-08, "input_cost_per_token": 4.2e-08, + "input_cost_per_token_batches": 2.1e-08, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.68e-07, + "output_cost_per_token_batches": 8.4e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, @@ -14681,13 +15905,21 @@ }, "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.4e-07, + "cache_read_input_token_cost_flex": 1.2e-07, + "cache_read_input_token_cost_priority": 4.2e-07, "input_cost_per_token": 9.6e-07, + "input_cost_per_token_batches": 4.8e-07, + "input_cost_per_token_flex": 4.8e-07, + "input_cost_per_token_priority": 1.68e-06, "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.84e-06, + "output_cost_per_token_batches": 1.92e-06, + "output_cost_per_token_flex": 1.92e-06, + "output_cost_per_token_priority": 6.72e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -14699,7 +15931,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 @@ -14708,7 +15939,6 @@ "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -14718,7 +15948,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.6e-06 }, @@ -14727,7 +15956,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-07 }, @@ -14736,7 +15964,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, @@ -14744,12 +15971,14 @@ "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-27", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14763,18 +15992,24 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, + "deprecation_date": "2027-04-27", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -14788,46 +16023,52 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", + "token_count_model": {"model":"anthropic.claude-sonnet-4-5-20250929-v1:0","litellm_provider":"bedrock"} }, "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-05-09", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "supports_pdf_input": true }, "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-05-09", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "supports_pdf_input": true }, "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -14838,7 +16079,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14848,7 +16088,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { @@ -14857,7 +16096,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14867,7 +16105,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14877,7 +16114,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { @@ -14886,7 +16122,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14895,7 +16130,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true @@ -14905,7 +16139,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -14915,18 +16148,17 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", @@ -14937,7 +16169,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", @@ -14945,11 +16176,11 @@ }, "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", @@ -14957,14 +16188,17 @@ }, "bedrock/us-west-2/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_batches": 3.1e-07, "input_cost_per_token_flex": 3.1e-07, + "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock", - "max_input_tokens": 163840, + "max_input_tokens": 156000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_batches": 9.25e-07, "output_cost_per_token_flex": 9.25e-07, + "output_cost_per_token_priority": 3.2375e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -14972,53 +16206,60 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/us-west-2/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-west-2/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-west-2/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_flex": 1.25e-06, @@ -15028,21 +16269,24 @@ }, "bedrock/us-west-2/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.25e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, @@ -15050,17 +16294,16 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", + "supports_audio_input": false, "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_audio_input": false, - "supports_response_schema": true, - "supports_vision": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" + "supports_vision": false }, "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0": { "cache_creation_input_token_cost": 1e-06, @@ -15069,7 +16312,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -15154,34 +16396,43 @@ "/v1/images/generations" ] }, - "cerebras/llama-3.3-70b": { - "input_cost_per_token": 8.5e-07, + "cerebras/llama-3.1-70b": { + "input_cost_per_token": 6e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_tool_choice": true }, - "cerebras/llama3.1-70b": { - "input_cost_per_token": 6e-07, + "cerebras/llama-3.1-8b": { + "input_cost_per_token": 1e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "cerebras/llama-3.3-70b": { + "deprecation_date": "2026-02-16", + "input_cost_per_token": 8.5e-07, + "litellm_provider": "cerebras", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_tool_choice": true }, "cerebras/llama3.1-8b": { + "deprecation_date": "2026-05-27", "input_cost_per_token": 1e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -15192,7 +16443,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.5e-07, "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras", @@ -15203,11 +16453,11 @@ "supports_tool_choice": true }, "cerebras/qwen-3-32b": { + "deprecation_date": "2026-02-16", "input_cost_per_token": 4e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://inference-docs.cerebras.ai/support/pricing", @@ -15220,7 +16470,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.49e-06, "source": "https://api.cerebras.ai/public/v1/models/qwen-3.8-27b", @@ -15236,7 +16485,6 @@ "litellm_provider": "nlp_cloud", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07 }, @@ -15252,6 +16500,8 @@ "/v1/audio/transcriptions" ], "deprecation_date": "2027-02-26", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-live-transcribe", "input_cost_per_second": 0.0001, "source": "https://developers.openai.com/api/docs/pricing" }, @@ -15267,7 +16517,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, @@ -15294,7 +16543,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, @@ -15319,11 +16567,12 @@ "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost_batches": 1.5e-07, "deprecation_date": "2026-11-30", + "deprecation_source": "https://platform.claude.com/docs/en/about-claude/model-deprecations", + "successor_model": "claude-sonnet-5-5", "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -15353,11 +16602,12 @@ "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost_batches": 1.5e-07, "deprecation_date": "2026-11-30", + "deprecation_source": "https://platform.claude.com/docs/en/about-claude/model-deprecations", + "successor_model": "claude-sonnet-5-5", "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -15393,7 +16643,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -15403,6 +16652,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -15437,7 +16687,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -15471,6 +16720,9 @@ "source": "https://platform.claude.com/docs/en/about-claude/pricing", "supports_web_search": true }, + "claude-sonnet-latest": { + "alias_of": "claude-sonnet-5-5" + }, "claude-sonnet-4-6": { "supports_web_search": true, "supports_anthropic_compaction": true, @@ -15484,7 +16736,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -15495,7 +16746,7 @@ }, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -15524,11 +16775,12 @@ "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "deprecation_date": "2027-04-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -15543,7 +16795,9 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, - "output_cost_per_token_batches": 7.5e-06 + "output_cost_per_token_batches": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", + "token_count_model": {"model":"anthropic.claude-sonnet-4-5-20250929-v1:0","litellm_provider":"bedrock"} }, "claude-opus-4-5-20251101": { "supports_web_search": true, @@ -15557,7 +16811,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -15591,7 +16844,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -15628,7 +16880,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -15671,7 +16922,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -15714,7 +16964,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -15742,7 +16991,6 @@ "us": 1.1 }, "supports_output_config": true, - "supports_speed": true, "prompt_cache_min_tokens": 2048, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, @@ -15758,7 +17006,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -15786,7 +17033,6 @@ "us": 1.1 }, "supports_output_config": true, - "supports_speed": true, "prompt_cache_min_tokens": 2048 }, "claude-fable-5": { @@ -15802,7 +17048,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -15847,7 +17092,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -15880,6 +17124,9 @@ "supports_native_structured_output": true, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, + "claude-fable-latest": { + "alias_of": "claude-fable-5-2" + }, "claude-opus-5-5": { "supports_web_search": true, "supports_anthropic_compaction": true, @@ -15893,7 +17140,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1e-05, @@ -15926,6 +17172,9 @@ "prompt_cache_min_tokens": 512, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, + "claude-opus-latest": { + "alias_of": "claude-opus-5-5" + }, "claude-opus-5": { "supports_web_search": true, "supports_anthropic_compaction": true, @@ -15939,7 +17188,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -15949,6 +17197,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -15987,7 +17236,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16030,7 +17278,8 @@ "output_cost_per_token": 0.0, "source": "https://developers.cloudflare.com/workers-ai/models/clef-omni/", "supports_audio_input": true, - "supports_video_input": true + "supports_video_input": true, + "supports_vision": true }, "cloudflare/@cf/cloudflare/clef-omni": { "input_cost_per_token": 1.5e-07, @@ -16040,7 +17289,8 @@ "output_cost_per_token": 0.0, "source": "https://developers.cloudflare.com/workers-ai/models/clef-omni/", "supports_audio_input": true, - "supports_video_input": true + "supports_video_input": true, + "supports_vision": true }, "cloudflare/clef": { "input_cost_per_token": 2.4e-07, @@ -16048,7 +17298,8 @@ "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, - "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true }, "cloudflare/clef-flash": { "input_cost_per_token": 9e-08, @@ -16056,7 +17307,8 @@ "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, - "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true }, "cloudflare/@cf/cloudflare/clef": { "input_cost_per_token": 2.4e-07, @@ -16064,7 +17316,8 @@ "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, - "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true }, "cloudflare/@cf/cloudflare/clef-flash": { "input_cost_per_token": 9e-08, @@ -16072,14 +17325,32 @@ "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, - "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true + }, + "cloudflare/clairic": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "extraction", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/models/clairic/", + "supports_vision": true + }, + "cloudflare/@cf/cloudflare/clairic": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "extraction", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/models/clairic/", + "supports_vision": true }, "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { "input_cost_per_token": 1.923e-06, "litellm_provider": "cloudflare", "max_input_tokens": 3072, "max_output_tokens": 3072, - "max_tokens": 3072, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -16089,7 +17360,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 2048, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -16099,7 +17369,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -16109,7 +17378,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -16119,7 +17387,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-07, "rpm": 300, @@ -16131,7 +17398,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -16141,7 +17407,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 80000, "max_output_tokens": 80000, - "max_tokens": 80000, "mode": "chat", "output_cost_per_token": 3.35e-07, "rpm": 300 @@ -16151,7 +17416,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-08, "rpm": 300 @@ -16161,7 +17425,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 15000, "max_output_tokens": 15000, - "max_tokens": 15000, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -16172,7 +17435,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "rpm": 20, @@ -16184,7 +17446,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 80000, "max_output_tokens": 80000, - "max_tokens": 80000, "mode": "chat", "output_cost_per_token": 4.881e-06, "rpm": 300, @@ -16195,7 +17456,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.87e-07, "rpm": 300 @@ -16205,7 +17465,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 60000, "max_output_tokens": 60000, - "max_tokens": 60000, "mode": "chat", "output_cost_per_token": 2.01e-07, "rpm": 300 @@ -16216,7 +17475,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "rpm": 20, @@ -16228,7 +17486,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-07, "rpm": 300, @@ -16240,7 +17497,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -16250,7 +17506,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 24000, "max_output_tokens": 24000, - "max_tokens": 24000, "mode": "chat", "output_cost_per_token": 2.253e-06, "rpm": 300, @@ -16261,7 +17516,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1.12e-07, "rpm": 300, @@ -16272,7 +17526,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-06, "rpm": 300 @@ -16283,7 +17536,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "rpm": 20, @@ -16295,7 +17547,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-06, "rpm": 300, @@ -16307,7 +17558,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.55e-07, "rpm": 300 @@ -16317,7 +17567,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.35e-07, "rpm": 300, @@ -16329,7 +17578,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 3500, "max_output_tokens": 3500, - "max_tokens": 3500, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -16339,7 +17587,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 3e-07, "rpm": 300, @@ -16351,7 +17598,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.55e-07, "rpm": 300, @@ -16362,7 +17608,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.76e-07, "rpm": 300, @@ -16373,7 +17618,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "rpm": 300, @@ -16385,7 +17629,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 8.5e-07, "rpm": 300, @@ -16396,18 +17639,18 @@ "litellm_provider": "cloudflare", "max_input_tokens": 24000, "max_output_tokens": 24000, - "max_tokens": 24000, "mode": "chat", "output_cost_per_token": 1e-06, "rpm": 300, "supports_reasoning": true }, "codestral/codestral-2405": { + "deprecation_date": "2025-06-16", + "deprecation_source": "https://docs.mistral.ai/getting-started/models/", "input_cost_per_token": 0.0, "litellm_provider": "codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/", @@ -16419,7 +17662,6 @@ "litellm_provider": "codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/", @@ -16431,7 +17673,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -16442,7 +17683,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -16452,7 +17692,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -16462,7 +17701,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -16472,7 +17710,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -16483,7 +17720,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -16494,7 +17730,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -16505,7 +17740,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "cohere", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -16517,7 +17751,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "cohere", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2048, @@ -16528,7 +17761,6 @@ "input_cost_per_token": 8e-08, "litellm_provider": "cohere", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2048, @@ -16550,7 +17782,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-cohere-rerank-3-5.md" @@ -16560,7 +17791,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -16572,7 +17802,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "source": "https://docs.cohere.com/docs/models" }, @@ -16581,7 +17810,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.cohere.com/docs/command-a-plus", @@ -16596,7 +17824,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06 }, @@ -16605,7 +17832,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -16616,7 +17842,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -16627,7 +17852,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.cohere.com/v2/docs/command-r7b", @@ -16640,7 +17864,7 @@ "input_cost_per_token": 1.12e-06, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.coralbricks.ai/pricing", @@ -16663,7 +17887,7 @@ "input_cost_per_token": 1.12e-06, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.coralbricks.ai/pricing", @@ -16686,7 +17910,7 @@ "input_cost_per_token": 1.12e-06, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.coralbricks.ai/pricing", @@ -16709,7 +17933,7 @@ "input_cost_per_token": 1e-08, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.coralbricks.ai/pricing", @@ -16732,7 +17956,7 @@ "input_cost_per_token": 1e-08, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.coralbricks.ai/pricing", @@ -16755,7 +17979,7 @@ "input_cost_per_token": 1e-08, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.coralbricks.ai/pricing", @@ -16774,13 +17998,15 @@ }, "computer-use-preview": { "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, + "fedramp_uplift_multiplier": 1.1, "supported_endpoints": [ "/v1/responses" ], @@ -16804,13 +18030,15 @@ }, "computer-use-preview-2025-03-11": { "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, + "fedramp_uplift_multiplier": 1.1, "supported_endpoints": [ "/v1/responses" ], @@ -16835,11 +18063,11 @@ "deepseek-chat": { "cache_read_input_token_cost": 2.8e-08, "deprecation_date": "2026-07-24", + "deprecation_source": "https://api-docs.deepseek.com/updates", "input_cost_per_token": 2.8e-07, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -16857,11 +18085,11 @@ "deepseek-reasoner": { "cache_read_input_token_cost": 2.8e-08, "deprecation_date": "2026-07-24", + "deprecation_source": "https://api-docs.deepseek.com/updates", "input_cost_per_token": 2.8e-07, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -16883,7 +18111,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16899,7 +18126,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16915,7 +18141,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16931,7 +18156,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 202745, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16947,7 +18171,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16963,7 +18186,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 229376, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16979,7 +18201,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -16991,7 +18212,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17020,7 +18240,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17050,7 +18269,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 30720, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17063,7 +18281,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17076,7 +18293,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17089,7 +18305,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -17103,7 +18318,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -17116,7 +18330,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17147,7 +18360,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17178,7 +18390,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17210,7 +18421,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -17224,7 +18434,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17237,7 +18446,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -17251,7 +18459,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -17264,7 +18471,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17275,7 +18481,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17324,7 +18529,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17369,7 +18573,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17418,7 +18621,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17463,7 +18665,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17500,7 +18701,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17537,7 +18737,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17575,7 +18774,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -17587,7 +18785,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -17600,7 +18797,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -17613,7 +18809,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -17627,7 +18822,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -17640,7 +18834,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -17653,7 +18846,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 260096, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17691,7 +18883,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17718,12 +18909,13 @@ ] }, "dashscope/qwen3.7-max": { + "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17737,7 +18929,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17773,7 +18964,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17784,6 +18974,9 @@ "supports_tool_choice": true, "supports_vision": true }, + "dashscope/qwen-max-latest": { + "alias_of": "dashscope/qwen3.8-max" + }, "dashscope/qwen3.8-flash": { "cache_creation_input_token_cost": 2e-07, "cache_read_input_token_cost": 1.6e-08, @@ -17791,7 +18984,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -17804,13 +18996,15 @@ "supports_vision": true, "supports_web_search": true }, + "dashscope/qwen-flash-latest": { + "alias_of": "dashscope/qwen3.8-flash" + }, "dashscope/qwen3.8-omni-flash": { "cache_read_input_token_cost": 1.6e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -17829,7 +19023,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 98304, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17840,25 +19033,31 @@ "dashscope/qwen-image-2.0": { "litellm_provider": "dashscope", "mode": "image_generation", - "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "output_cost_per_image": 0.035, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supported_endpoints": [ - "/v1/images/generations" + "/v1/images/generations", + "/v1/images/edits" ] }, "dashscope/qwen-image-2.0-pro": { "litellm_provider": "dashscope", "mode": "image_generation", - "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "output_cost_per_image": 0.075, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supported_endpoints": [ - "/v1/images/generations" + "/v1/images/generations", + "/v1/images/edits" ] }, "dashscope/qwen-image-3.0": { "litellm_provider": "dashscope", "mode": "image_generation", - "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "output_cost_per_image": 0.03, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supported_endpoints": [ - "/v1/images/generations" + "/v1/images/generations", + "/v1/images/edits" ] }, "dashscope/qwen-image-3.0-pro": { @@ -17866,16 +19065,337 @@ "mode": "image_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supported_endpoints": [ - "/v1/images/generations" + "/v1/images/generations", + "/v1/images/edits" + ] + }, + "dashscope/qwen3-tts-flash": { + "input_cost_per_character": 1e-05, + "litellm_provider": "dashscope", + "mode": "audio_speech", + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "dashscope/qwen-audio-3.1-tts-flash": { + "input_cost_per_token": 2.3e-07, + "output_cost_per_token": 1.87e-06, + "litellm_provider": "dashscope", + "mode": "audio_speech", + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "dashscope/qwen-audio-3.1-tts-plus": { + "input_cost_per_character": 3e-05, + "litellm_provider": "dashscope", + "mode": "audio_speech", + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "dashscope/qwen-audio-3.0-tts-plus": { + "input_cost_per_character": 2e-05, + "litellm_provider": "dashscope", + "mode": "audio_speech", + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supported_endpoints": [ + "/v1/audio/speech" ] }, + "dashscope/qwen-audio-3.0-tts-flash": { + "input_cost_per_character": 1.5e-05, + "litellm_provider": "dashscope", + "mode": "audio_speech", + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "dashscope/wan3.0-video": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", + "output_cost_per_second": 0.165025, + "output_cost_per_second_480p": 0.041256, + "output_cost_per_second_720p": 0.082513, + "output_cost_per_second_1080p": 0.165025, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan3.0-video-prime": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", + "output_cost_per_second": 0.254399, + "output_cost_per_second_480p": 0.0636, + "output_cost_per_second_720p": 0.127199, + "output_cost_per_second_1080p": 0.254399, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.1-t2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 text-to-video. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.1-i2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 image-to-video from a first frame. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.1-r2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.0-t2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.0-i2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.0-r2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan2.7-t2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan2.7-i2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan2.7-r2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "Wan 2.7 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, "qwencloud/deepseek-v4-flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.qwencloud.com/models", @@ -17891,7 +19411,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.qwencloud.com/models", @@ -17907,7 +19426,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.qwencloud.com/models", @@ -17923,7 +19441,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 202745, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.qwencloud.com/models", @@ -17939,7 +19456,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.qwencloud.com/models", @@ -17955,7 +19471,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 229376, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.qwencloud.com/models", @@ -17971,7 +19486,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.qwencloud.com/models", @@ -17983,7 +19497,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18012,7 +19525,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18042,7 +19554,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 30720, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.qwencloud.com/models", @@ -18055,7 +19566,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -18068,7 +19578,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -18081,7 +19590,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -18095,7 +19603,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -18108,7 +19615,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18139,7 +19645,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18170,7 +19675,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18202,7 +19706,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -18216,7 +19719,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.qwencloud.com/models", @@ -18229,7 +19731,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -18243,7 +19744,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -18256,7 +19756,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18267,7 +19766,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18316,7 +19814,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18361,7 +19858,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18410,7 +19906,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18455,7 +19950,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18492,7 +19986,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18529,7 +20022,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18567,7 +20059,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -18579,7 +20070,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -18592,7 +20082,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.qwencloud.com/models", @@ -18605,7 +20094,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.qwencloud.com/models", @@ -18619,7 +20107,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.qwencloud.com/models", @@ -18632,7 +20119,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.qwencloud.com/models", @@ -18645,7 +20131,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 260096, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18683,7 +20168,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18710,12 +20194,13 @@ ] }, "qwencloud/qwen3.7-max": { + "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.qwencloud.com/models", @@ -18729,7 +20214,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18765,7 +20249,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.qwencloud.com/models", @@ -18781,7 +20264,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 98304, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.qwencloud.com/models", @@ -18821,13 +20303,287 @@ "/v1/images/generations" ] }, + "qwencloud/wan3.0-video": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", + "output_cost_per_second": 0.2, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.2, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan3.0-video-prime": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", + "output_cost_per_second": 0.28, + "output_cost_per_second_480p": 0.068, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.28, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.1-t2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", + "output_cost_per_second": 0.18, + "output_cost_per_second_480p": 0.07, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.18, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 text-to-video. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.1-i2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", + "output_cost_per_second": 0.18, + "output_cost_per_second_480p": 0.07, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.18, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 image-to-video from a first frame. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.1-r2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", + "output_cost_per_second": 0.18, + "output_cost_per_second_480p": 0.07, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.18, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.0-t2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", + "output_cost_per_second": 0.24, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.24, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 text-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.0-i2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", + "output_cost_per_second": 0.24, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.24, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.0-r2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", + "output_cost_per_second": 0.24, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.24, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan2.7-t2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", + "output_cost_per_second": 0.15, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.15, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 text-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan2.7-i2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", + "output_cost_per_second": 0.15, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.15, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan2.7-r2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", + "output_cost_per_second": 0.15, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.15, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "Wan 2.7 reference-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, "qwen_ai_platform/deepseek-v4-flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18843,7 +20599,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18859,7 +20614,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18875,7 +20629,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 202745, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18891,7 +20644,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18907,7 +20659,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 229376, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18923,7 +20674,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18935,7 +20685,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18964,7 +20713,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18994,7 +20742,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 30720, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19007,7 +20754,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19020,7 +20766,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19033,7 +20778,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -19047,7 +20791,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -19060,7 +20803,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19091,7 +20833,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19122,7 +20863,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19154,7 +20894,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -19168,7 +20907,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19181,7 +20919,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -19195,7 +20932,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -19208,7 +20944,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19219,7 +20954,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19268,7 +21002,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19313,7 +21046,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19362,7 +21094,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19407,7 +21138,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19444,7 +21174,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19481,7 +21210,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19519,7 +21247,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -19531,7 +21258,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -19544,7 +21270,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -19557,7 +21282,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -19571,7 +21295,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -19584,7 +21307,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -19597,7 +21319,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 260096, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19635,7 +21356,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19662,12 +21382,13 @@ ] }, "qwen_ai_platform/qwen3.7-max": { + "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19681,7 +21402,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -19717,7 +21437,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19735,7 +21454,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -19754,7 +21472,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -19773,7 +21490,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 98304, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19813,6 +21529,281 @@ "/v1/images/generations" ] }, + "qwen_ai_platform/wan3.0-video": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", + "output_cost_per_second": 0.165025, + "output_cost_per_second_480p": 0.041256, + "output_cost_per_second_720p": 0.082513, + "output_cost_per_second_1080p": 0.165025, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan3.0-video-prime": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", + "output_cost_per_second": 0.254399, + "output_cost_per_second_480p": 0.0636, + "output_cost_per_second_720p": 0.127199, + "output_cost_per_second_1080p": 0.254399, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.1-t2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 text-to-video. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.1-i2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 image-to-video from a first frame. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.1-r2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.0-t2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.0-i2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.0-r2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan2.7-t2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan2.7-i2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan2.7-r2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "Wan 2.7 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, "databricks/databricks-bge-large-en": { "cache_creation_input_token_cost": 1.0003e-07, "cache_read_input_token_cost": 1.0003e-07, @@ -19820,7 +21811,6 @@ "input_dbu_cost_per_token": 1.429e-06, "litellm_provider": "databricks", "max_input_tokens": 512, - "max_tokens": 512, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -19831,20 +21821,20 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-claude-fable-5": { - "cache_creation_input_token_cost": 1.250004e-05, + "cache_creation_input_token_cost": 1.249997e-05, + "cache_creation_input_token_cost_above_1hr": 1.999998e-05, "cache_read_input_token_cost": 1.00002e-06, - "input_cost_per_token": 1.000006e-05, - "input_dbu_cost_per_token": 0.000142858, + "input_cost_per_token": 9.99999e-06, + "input_dbu_cost_per_token": 0.00014286, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 5.000002e-05, - "output_dbu_cost_per_token": 0.000714286, + "output_dbu_cost_per_token": 0.00071429, "prompt_cache_min_tokens": 512, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, @@ -19860,20 +21850,20 @@ "thinking_always_on": true }, "databricks/databricks-claude-fable-5-1": { - "cache_creation_input_token_cost": 1.250004e-05, - "cache_read_input_token_cost": 2.5004e-07, - "input_cost_per_token": 1.000006e-05, - "input_dbu_cost_per_token": 0.000142858, + "cache_creation_input_token_cost": 1.249997e-05, + "cache_creation_input_token_cost_above_1hr": 1.999998e-05, + "cache_read_input_token_cost": 2.4997e-07, + "input_cost_per_token": 9.99999e-06, + "input_dbu_cost_per_token": 0.00014286, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 5.000002e-05, - "output_dbu_cost_per_token": 0.000714286, + "output_dbu_cost_per_token": 0.00071429, "prompt_cache_min_tokens": 512, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, @@ -19889,15 +21879,18 @@ "supports_vision": true, "thinking_always_on": true }, + "databricks/claude-fable-latest": { + "alias_of": "databricks/databricks-claude-fable-5-2" + }, "databricks/databricks-claude-haiku-4-5": { "cache_creation_input_token_cost": 1.24999e-06, + "cache_creation_input_token_cost_above_1hr": 1.99997e-06, "cache_read_input_token_cost": 1.0003e-07, "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -19915,19 +21908,19 @@ }, "databricks/databricks-claude-opus-4": { "cache_creation_input_token_cost": 1.874999e-05, + "cache_creation_input_token_cost_above_1hr": 2.999997e-05, "cache_read_input_token_cost": 1.50003e-06, - "input_cost_per_token": 1.5000020000000002e-05, - "input_dbu_cost_per_token": 0.000214286, + "input_cost_per_token": 1.500002e-05, + "input_dbu_cost_per_token": 0.00021429, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 7.500003000000001e-05, - "output_dbu_cost_per_token": 0.001071429, + "output_cost_per_token": 7.50001e-05, + "output_dbu_cost_per_token": 0.0010714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -19939,19 +21932,19 @@ }, "databricks/databricks-claude-opus-4-1": { "cache_creation_input_token_cost": 1.874999e-05, + "cache_creation_input_token_cost_above_1hr": 2.999997e-05, "cache_read_input_token_cost": 1.50003e-06, - "input_cost_per_token": 1.5000020000000002e-05, - "input_dbu_cost_per_token": 0.000214286, + "input_cost_per_token": 1.500002e-05, + "input_dbu_cost_per_token": 0.00021429, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 7.500003000000001e-05, - "output_dbu_cost_per_token": 0.001071429, + "output_cost_per_token": 7.50001e-05, + "output_dbu_cost_per_token": 0.0010714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -19963,19 +21956,19 @@ }, "databricks/databricks-claude-opus-4-5": { "cache_creation_input_token_cost": 6.25002e-06, + "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 2.5000010000000002e-05, - "output_dbu_cost_per_token": 0.000357143, + "output_cost_per_token": 2.500001e-05, + "output_dbu_cost_per_token": 0.00035714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -19988,21 +21981,21 @@ }, "databricks/databricks-claude-opus-4-6": { "cache_creation_input_token_cost": 6.25002e-06, + "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 2.5000010000000002e-05, - "output_dbu_cost_per_token": 0.000357143, + "output_cost_per_token": 2.500001e-05, + "output_dbu_cost_per_token": 0.00035714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, "supports_legacy_thinking": true, "supports_prompt_caching": true, @@ -20013,19 +22006,19 @@ }, "databricks/databricks-claude-opus-4-7": { "cache_creation_input_token_cost": 6.25002e-06, + "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 2.500001e-05, - "output_dbu_cost_per_token": 0.000357143, + "output_dbu_cost_per_token": 0.00035714, "prompt_cache_min_tokens": 2048, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, @@ -20040,19 +22033,19 @@ }, "databricks/databricks-claude-opus-4-8": { "cache_creation_input_token_cost": 6.25002e-06, + "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 2.500001e-05, - "output_dbu_cost_per_token": 0.000357143, + "output_dbu_cost_per_token": 0.00035714, "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, @@ -20068,22 +22061,23 @@ }, "databricks/databricks-claude-opus-5": { "cache_creation_input_token_cost": 6.25002e-06, + "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 2.500001e-05, - "output_dbu_cost_per_token": 0.000357143, + "output_dbu_cost_per_token": 0.00035714, "prompt_cache_min_tokens": 512, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_function_calling": true, "supports_mid_conversation_system": true, @@ -20103,7 +22097,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, @@ -20129,21 +22122,24 @@ "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, + "databricks/claude-opus-latest": { + "alias_of": "databricks/databricks-claude-opus-5-5" + }, "databricks/databricks-claude-sonnet-4": { "cache_creation_input_token_cost": 3.74997e-06, "cache_read_input_token_cost": 3.0002e-07, "deprecation_date": "2026-10-09", - "input_cost_per_token": 2.9999900000000002e-06, + "successor_model": "databricks/databricks-claude-sonnet-5", + "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, + "output_cost_per_token": 1.500002e-05, "output_dbu_cost_per_token": 0.000214286, "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", @@ -20162,7 +22158,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20179,19 +22174,19 @@ }, "databricks/databricks-claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.74997e-06, + "cache_creation_input_token_cost_above_1hr": 5.99998e-06, "cache_read_input_token_cost": 3.0002e-07, - "input_cost_per_token": 2.9999900000000002e-06, + "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, - "output_dbu_cost_per_token": 0.000214286, + "output_cost_per_token": 1.500002e-05, + "output_dbu_cost_per_token": 0.00021429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -20203,21 +22198,21 @@ }, "databricks/databricks-claude-sonnet-4-6": { "cache_creation_input_token_cost": 3.74997e-06, + "cache_creation_input_token_cost_above_1hr": 5.99998e-06, "cache_read_input_token_cost": 3.0002e-07, - "input_cost_per_token": 2.9999900000000002e-06, + "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, - "output_dbu_cost_per_token": 0.000214286, + "output_cost_per_token": 1.500002e-05, + "output_dbu_cost_per_token": 0.00021429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, "supports_legacy_thinking": true, "supports_prompt_caching": true, @@ -20227,23 +22222,24 @@ "prompt_cache_min_tokens": 1024 }, "databricks/databricks-claude-sonnet-5": { - "cache_creation_input_token_cost": 3.74997e-06, - "cache_read_input_token_cost": 3.0002e-07, - "input_cost_per_token": 2.99999e-06, - "input_dbu_cost_per_token": 4.2857e-05, + "cache_creation_input_token_cost": 2.49998e-06, + "cache_creation_input_token_cost_above_1hr": 4.00001e-06, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_token": 1.99997e-06, + "input_dbu_cost_per_token": 2.8571e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { - "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. Introductory launch rates of 28.571 input / 142.857 output / 35.714 cache write / 2.857 cache read DBU run through 2026-08-31; the standard rates are listed here because entries carry no expiry date." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 1.500002e-05, - "output_dbu_cost_per_token": 0.000214286, + "output_cost_per_token": 9.99999e-06, + "output_dbu_cost_per_token": 0.00014286, "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_function_calling": true, "supports_mid_conversation_system": true, @@ -20257,19 +22253,22 @@ "databricks/databricks-deepseek-v4-flash-0731": { "cache_creation_input_token_cost": 1.4e-07, "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-11-05", + "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "input_cost_per_token": 1.4e-07, "input_dbu_cost_per_token": 2e-06, "litellm_provider": "databricks", + "token_count_framing": 97, "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)." }, "mode": "chat", "output_cost_per_token": 2.8e-07, "output_dbu_cost_per_token": 4e-06, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "successor_model": "databricks/databricks-deepseek-v4-1-flash-1017", "supported_modalities": [ "text" ], @@ -20282,22 +22281,33 @@ "supports_tool_choice": true, "supports_vision": false }, + "databricks/system.ai.deepseek-v4-flash-0731": { + "deprecation_date": "2026-11-05", + "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/retired-models-policy", + "litellm_provider": "databricks", + "mode": "chat", + "source": "https://docs.databricks.com/aws/en/machine-learning/retired-models-policy", + "successor_model": "databricks/databricks-deepseek-v4-1-flash-1017", + "token_count_framing": 97 + }, "databricks/databricks-deepseek-v4-pro-0813": { "cache_creation_input_token_cost": 1.31999e-06, "cache_read_input_token_cost": 1.3202e-07, + "deprecation_date": "2026-10-30", + "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "input_cost_per_token": 1.31999e-06, "input_dbu_cost_per_token": 1.8857e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)." }, "mode": "chat", "output_cost_per_token": 3.95997e-06, "output_dbu_cost_per_token": 5.6571e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "successor_model": "databricks/databricks-deepseek-v4-1-flash-1017", "supported_modalities": [ "text" ], @@ -20314,12 +22324,12 @@ "cache_creation_input_token_cost": 3.0002e-07, "cache_read_input_token_cost": 3.0002e-08, "deprecation_date": "2026-10-02", + "successor_model": "databricks/databricks-gemini-3-5-flash", "input_cost_per_token": 3.0001999999999996e-07, "input_dbu_cost_per_token": 4.285999999999999e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20353,7 +22363,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20382,13 +22391,15 @@ }, "databricks/databricks-gemini-3-1-flash-lite": { "cache_creation_input_token_cost": 3.1248e-07, + "cache_read_input_audio_token_cost": 6.251e-08, "cache_read_input_token_cost": 3.122e-08, + "input_cost_per_audio_token": 6.2503e-07, + "input_cost_per_image_token": 3.1248e-07, "input_cost_per_token": 3.1248e-07, "input_dbu_cost_per_token": 4.464e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20410,17 +22421,28 @@ ], "supports_vision": true, "supports_audio_input": true, - "supports_video_input": true + "supports_video_input": true, + "input_cost_per_token_priority": 5.6252e-07, + "output_cost_per_token_priority": 3.37498e-06, + "cache_read_input_token_cost_priority": 5.628e-08, + "cache_creation_input_token_cost_priority": 5.6252e-07, + "input_cost_per_audio_token_priority": 1.12497e-06, + "cache_read_input_audio_token_cost_priority": 1.1249e-07 }, "databricks/databricks-gemini-3-1-flash-image": { + "cache_creation_input_token_cost": 6.2503e-07, + "cache_read_input_token_cost": 6.2503e-07, + "input_cost_per_image_token": 6.2503e-07, + "input_cost_per_token": 6.2503e-07, "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "metadata": { - "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", + "output_cost_per_image_token": 7.50001e-05, + "output_cost_per_token": 3.74997e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", @@ -20434,14 +22456,19 @@ "supports_vision": true }, "databricks/databricks-gemini-3-pro-image": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 2.49998e-06, + "input_cost_per_image_token": 2.49998e-06, + "input_cost_per_token": 2.49998e-06, "litellm_provider": "databricks", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "metadata": { - "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", + "output_cost_per_image_token": 0.0001500002, + "output_cost_per_token": 1.500002e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", @@ -20457,23 +22484,21 @@ "databricks/databricks-gemini-3-1-pro": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 2.4997e-07, + "cache_read_input_token_cost_above_200k_tokens": 5.0001e-07, "input_cost_per_token": 2.49998e-06, + "input_cost_per_token_above_200k_tokens": 5.00003e-06, "input_dbu_cost_per_token": 3.5714e-05, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, + "output_cost_per_token": 1.500002e-05, + "output_cost_per_token_above_200k_tokens": 2.25e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_reasoning": true, "supported_modalities": [ "text", "image", @@ -20483,19 +22508,32 @@ "supported_output_modalities": [ "text" ], - "supports_vision": true, "supports_audio_input": true, - "supports_video_input": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "input_cost_per_token_priority": 4.50002e-06, + "output_cost_per_token_priority": 2.699998e-05, + "cache_read_input_token_cost_priority": 4.5003e-07, + "cache_creation_input_token_cost_priority": 4.50002e-06, + "input_cost_per_token_above_200k_tokens_priority": 8.99997e-06, + "output_cost_per_token_above_200k_tokens_priority": 4.049997e-05, + "cache_read_input_token_cost_above_200k_tokens_priority": 8.9999e-07 }, "databricks/databricks-gemini-3-flash": { "cache_creation_input_token_cost": 6.2503e-07, + "cache_read_input_audio_token_cost": 1.2502e-07, "cache_read_input_token_cost": 6.251e-08, + "input_cost_per_audio_token": 1.24999e-06, + "input_cost_per_image_token": 6.2503e-07, "input_cost_per_token": 6.2503e-07, "input_dbu_cost_per_token": 8.929e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20517,7 +22555,13 @@ ], "supports_vision": true, "supports_audio_input": true, - "supports_video_input": true + "supports_video_input": true, + "input_cost_per_token_priority": 1.12497e-06, + "output_cost_per_token_priority": 6.75003e-06, + "cache_read_input_token_cost_priority": 1.1249e-07, + "cache_creation_input_token_cost_priority": 1.12497e-06, + "input_cost_per_audio_token_priority": 2.25001e-06, + "cache_read_input_audio_token_cost_priority": 2.2498e-07 }, "databricks/databricks-gemini-3-pro": { "cache_creation_input_token_cost": 2.49998e-06, @@ -20527,7 +22571,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20540,15 +22583,18 @@ "supports_tool_choice": true }, "databricks/databricks-gemini-3-8-flash": { + "cache_creation_input_token_cost": 7.4998e-07, + "cache_read_input_token_cost": 7.497e-08, + "input_cost_per_token": 7.4998e-07, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { - "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "output_cost_per_token": 3.74997e-06, + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -20560,19 +22606,29 @@ ], "supports_function_calling": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 1.35002e-06, + "output_cost_per_token_priority": 6.75003e-06, + "cache_read_input_token_cost_priority": 1.3503e-07, + "cache_creation_input_token_cost_priority": 1.35002e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-7-flash": { + "cache_creation_input_token_cost": 7.4998e-07, + "cache_read_input_token_cost": 7.497e-08, + "input_cost_per_token": 7.4998e-07, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { - "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "output_cost_per_token": 3.74997e-06, + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -20584,25 +22640,31 @@ ], "supports_function_calling": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 1.35002e-06, + "output_cost_per_token_priority": 6.75003e-06, + "cache_read_input_token_cost_priority": 1.3503e-07, + "cache_creation_input_token_cost_priority": 1.35002e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-6-flash": { - "cache_creation_input_token_cost": 1.87502e-06, - "cache_read_input_token_cost": 1.8753e-07, - "input_cost_per_token": 1.87502e-06, - "input_dbu_cost_per_token": 2.6786e-05, + "cache_creation_input_token_cost": 7.4998e-07, + "cache_read_input_token_cost": 7.497e-08, + "input_cost_per_token": 7.4998e-07, + "input_dbu_cost_per_token": 1.0714e-05, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 9.37503e-06, - "output_dbu_cost_per_token": 0.000133929, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "output_cost_per_token": 3.74997e-06, + "output_dbu_cost_per_token": 5.3571e-05, + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -20615,8 +22677,15 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 1.35002e-06, + "output_cost_per_token_priority": 6.75003e-06, + "cache_read_input_token_cost_priority": 1.3503e-07, + "cache_creation_input_token_cost_priority": 1.35002e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-5-flash": { "cache_creation_input_token_cost": 1.87502e-06, @@ -20626,14 +22695,13 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 1.124998e-05, "output_dbu_cost_per_token": 0.000160714, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -20647,7 +22715,13 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 3.37498e-06, + "output_cost_per_token_priority": 2.025002e-05, + "cache_read_input_token_cost_priority": 3.3747e-07, + "cache_creation_input_token_cost_priority": 3.37498e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-5-flash-lite": { "cache_creation_input_token_cost": 3.7499e-07, @@ -20657,14 +22731,13 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 3.12501e-06, "output_dbu_cost_per_token": 4.4643e-05, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -20678,18 +22751,24 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 6.7501e-07, + "output_cost_per_token_priority": 5.62499e-06, + "cache_read_input_token_cost_priority": 6.748e-08, + "cache_creation_input_token_cost_priority": 6.7501e-07, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemma-3-12b": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, - "input_cost_per_token": 1.5000999999999998e-07, + "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20706,7 +22785,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference." }, @@ -20724,7 +22802,14 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "input_cost_per_token_priority": 2.45e-06, + "output_cost_per_token_priority": 7.7e-06, + "cache_read_input_token_cost_priority": 4.55e-07, + "cache_creation_input_token_cost_priority": 2.45e-06, + "deprecation_date": "2027-02-04", + "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "successor_model": "databricks/databricks-glm-5-3" }, "databricks/databricks-glm-5-3": { "cache_creation_input_token_cost": 1.4e-06, @@ -20734,7 +22819,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, @@ -20755,7 +22839,14 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false, - "thinking_always_on": true + "thinking_always_on": true, + "input_cost_per_token_priority": 2.45e-06, + "output_cost_per_token_priority": 7.7e-06, + "cache_read_input_token_cost_priority": 4.55e-07, + "cache_creation_input_token_cost_priority": 2.45e-06 + }, + "databricks/glm-latest": { + "alias_of": "databricks/databricks-glm-5-3" }, "databricks/databricks-glm-5-3-flash": { "cache_creation_input_token_cost": 1.5001e-07, @@ -20765,7 +22856,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, @@ -20785,7 +22875,14 @@ "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "thinking_always_on": true + "thinking_always_on": true, + "input_cost_per_token_priority": 2.625e-07, + "output_cost_per_token_priority": 8.75e-07, + "cache_read_input_token_cost_priority": 5.25e-08, + "cache_creation_input_token_cost_priority": 2.625e-07 + }, + "databricks/glm-flash-latest": { + "alias_of": "databricks/databricks-glm-5-3-flash" }, "databricks/databricks-gpt-5": { "cache_creation_input_token_cost": 1.24999e-06, @@ -20795,17 +22892,20 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 9.999990000000002e-06, + "output_cost_per_token": 9.99999e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "input_cost_per_token_priority": 2.49998e-06, + "output_cost_per_token_priority": 1.999998e-05, + "cache_read_input_token_cost_priority": 2.4997e-07, + "cache_creation_input_token_cost_priority": 2.49998e-06 }, "databricks/databricks-gpt-5-1": { "cache_creation_input_token_cost": 1.24999e-06, @@ -20815,17 +22915,20 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 9.999990000000002e-06, + "output_cost_per_token": 9.99999e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "input_cost_per_token_priority": 2.49998e-06, + "output_cost_per_token_priority": 1.999998e-05, + "cache_read_input_token_cost_priority": 2.4997e-07, + "cache_creation_input_token_cost_priority": 2.49998e-06 }, "databricks/databricks-gpt-5-2": { "cache_creation_input_token_cost": 1.75e-06, @@ -20835,7 +22938,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20845,7 +22947,11 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "input_cost_per_token_priority": 3.5e-06, + "output_cost_per_token_priority": 2.8e-05, + "cache_read_input_token_cost_priority": 3.5e-07, + "cache_creation_input_token_cost_priority": 3.5e-06 }, "databricks/databricks-gpt-5-3-codex": { "cache_creation_input_token_cost": 1.75e-06, @@ -20855,7 +22961,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20865,22 +22970,28 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "input_cost_per_token_priority": 3.5e-06, + "output_cost_per_token_priority": 2.8e-05, + "cache_read_input_token_cost_priority": 3.5e-07, + "cache_creation_input_token_cost_priority": 3.5e-06 }, "databricks/databricks-gpt-5-4": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 2.4997e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.0001e-07, "input_cost_per_token": 2.49998e-06, + "input_cost_per_token_above_272k_tokens": 5.00003e-06, "input_dbu_cost_per_token": 3.5714e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, + "output_cost_per_token": 1.500002e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ @@ -20894,7 +23005,14 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 5.00003e-06, + "output_cost_per_token_priority": 2.999997e-05, + "cache_read_input_token_cost_priority": 5.0001e-07, + "cache_creation_input_token_cost_priority": 5.00003e-06, + "input_cost_per_token_above_272k_tokens_priority": 5.00003e-06, + "output_cost_per_token_above_272k_tokens_priority": 2.999997e-05, + "cache_read_input_token_cost_above_272k_tokens_priority": 5.0001e-07 }, "databricks/databricks-gpt-5-4-mini": { "cache_creation_input_token_cost": 7.4998e-07, @@ -20904,7 +23022,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20923,7 +23040,14 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 1.50003e-06, + "output_cost_per_token_priority": 8.99997e-06, + "cache_read_input_token_cost_priority": 1.5001e-07, + "cache_creation_input_token_cost_priority": 1.50003e-06 + }, + "databricks/gpt-mini-latest": { + "alias_of": "databricks/databricks-gpt-5-4-mini" }, "databricks/databricks-gpt-5-4-nano": { "cache_creation_input_token_cost": 1.9999e-07, @@ -20933,7 +23057,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -20956,18 +23079,21 @@ }, "databricks/databricks-gpt-5-6-sol": { "cache_creation_input_token_cost": 5.00003e-06, + "cache_creation_input_token_cost_above_272k_tokens": 9.99999e-06, "cache_read_input_token_cost": 3.9998e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.0003e-07, "input_cost_per_token": 4.00001e-06, + "input_cost_per_token_above_272k_tokens": 8.00002e-06, "input_dbu_cost_per_token": 5.7143e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. Rates reflect OpenAI's promotional pricing in effect through November 21, 2026; afterwards input, cache and Batch rates are 25% higher and output rates 50% higher." }, "mode": "chat", "output_cost_per_token": 1.999998e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, "output_dbu_cost_per_token": 0.000285714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ @@ -20981,23 +23107,34 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 8.00002e-06, + "output_cost_per_token_priority": 4.000003e-05, + "cache_read_input_token_cost_priority": 8.0003e-07, + "cache_creation_input_token_cost_priority": 9.99999e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.599997e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.000001e-05, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.59999e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.999998e-05 }, "databricks/databricks-gpt-5-6-terra": { - "cache_creation_input_token_cost": 3.12501e-06, - "cache_read_input_token_cost": 2.4997e-07, - "input_cost_per_token": 2.49998e-06, - "input_dbu_cost_per_token": 3.5714e-05, + "cache_creation_input_token_cost": 2.49998e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.00003e-06, + "cache_read_input_token_cost": 1.9999e-07, + "cache_read_input_token_cost_above_272k_tokens": 3.9998e-07, + "input_cost_per_token": 1.99997e-06, + "input_cost_per_token_above_272k_tokens": 4.00001e-06, + "input_dbu_cost_per_token": 2.8571e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 1.500002e-05, - "output_dbu_cost_per_token": 0.000214286, + "output_cost_per_token": 1.200003e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_dbu_cost_per_token": 0.000171429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", @@ -21010,23 +23147,34 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 4.00001e-06, + "output_cost_per_token_priority": 2.399999e-05, + "cache_read_input_token_cost_priority": 3.9998e-07, + "cache_creation_input_token_cost_priority": 5.00003e-06, + "input_cost_per_token_above_272k_tokens_priority": 8.00002e-06, + "output_cost_per_token_above_272k_tokens_priority": 3.600002e-05, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.0003e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 9.99999e-06 }, "databricks/databricks-gpt-5-6-luna": { - "cache_creation_input_token_cost": 1.24999e-06, - "cache_read_input_token_cost": 1.0003e-07, - "input_cost_per_token": 1.00002e-06, - "input_dbu_cost_per_token": 1.4286e-05, + "cache_creation_input_token_cost": 2.4997e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5.0001e-07, + "cache_read_input_token_cost": 2.002e-08, + "cache_read_input_token_cost_above_272k_tokens": 3.997e-08, + "input_cost_per_token": 1.9999e-07, + "input_cost_per_token_above_272k_tokens": 3.9998e-07, + "input_dbu_cost_per_token": 2.857e-06, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 5.99998e-06, - "output_dbu_cost_per_token": 8.5714e-05, + "output_cost_per_token": 1.20001e-06, + "output_cost_per_token_above_272k_tokens": 1.79998e-06, + "output_dbu_cost_per_token": 1.7143e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", @@ -21039,22 +23187,32 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 3.9998e-07, + "output_cost_per_token_priority": 2.40002e-06, + "cache_read_input_token_cost_priority": 3.997e-08, + "cache_creation_input_token_cost_priority": 5.0001e-07, + "input_cost_per_token_above_272k_tokens_priority": 8.0003e-07, + "output_cost_per_token_above_272k_tokens_priority": 3.60003e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.001e-08, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.00002e-06 }, "databricks/databricks-gpt-5-5": { "cache_creation_input_token_cost": 5.00003e-06, "cache_read_input_token_cost": 5.0001e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.00002e-06, "input_cost_per_token": 5.00003e-06, + "input_cost_per_token_above_272k_tokens": 9.99999e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "responses", "output_cost_per_token": 2.999997e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_dbu_cost_per_token": 0.000428571, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ @@ -21068,23 +23226,31 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 1.249997e-05, + "output_cost_per_token_priority": 7.50001e-05, + "cache_read_input_token_cost_priority": 1.24999e-06, + "cache_creation_input_token_cost_priority": 1.249997e-05, + "input_cost_per_token_above_272k_tokens_priority": 1.249997e-05, + "output_cost_per_token_above_272k_tokens_priority": 7.50001e-05, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.24999e-06 }, "databricks/databricks-gpt-5-5-pro": { "cache_creation_input_token_cost": 2.999997e-05, "cache_read_input_token_cost": 2.999997e-05, "input_cost_per_token": 2.999997e-05, - "input_dbu_cost_per_token": 0.000428571, + "input_cost_per_token_above_272k_tokens": 6e-05, + "input_dbu_cost_per_token": 0.00042857, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "responses", - "output_cost_per_token": 0.00018000003, - "output_dbu_cost_per_token": 0.002571429, + "output_cost_per_token": 0.0001800001, + "output_cost_per_token_above_272k_tokens": 0.00027, + "output_dbu_cost_per_token": 0.0025714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", @@ -21102,22 +23268,25 @@ "databricks/databricks-gpt-5-mini": { "cache_creation_input_token_cost": 2.4997e-07, "cache_read_input_token_cost": 2.499e-08, - "input_cost_per_token": 2.4997000000000006e-07, + "input_cost_per_token": 2.4997e-07, "input_dbu_cost_per_token": 3.571e-06, "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.9999700000000004e-06, + "output_cost_per_token": 1.99997e-06, "output_dbu_cost_per_token": 2.8571e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "input_cost_per_token_priority": 4.5003e-07, + "output_cost_per_token_priority": 3.60003e-06, + "cache_read_input_token_cost_priority": 4.501e-08, + "cache_creation_input_token_cost_priority": 4.5003e-07 }, "databricks/databricks-gpt-5-nano": { "cache_creation_input_token_cost": 4.998e-08, @@ -21127,12 +23296,11 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 3.9998000000000007e-07, + "output_cost_per_token": 3.9998e-07, "output_dbu_cost_per_token": 5.714000000000001e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, @@ -21142,12 +23310,11 @@ "databricks/databricks-gpt-oss-120b": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, - "input_cost_per_token": 1.5000999999999998e-07, + "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21164,12 +23331,11 @@ "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 3.0001999999999996e-07, + "output_cost_per_token": 3.0002e-07, "output_dbu_cost_per_token": 4.285999999999999e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, @@ -21202,11 +23368,10 @@ "databricks/databricks-gte-large-en": { "cache_creation_input_token_cost": 1.2999e-07, "cache_read_input_token_cost": 1.2999e-07, - "input_cost_per_token": 1.2999000000000001e-07, + "input_cost_per_token": 1.2999e-07, "input_dbu_cost_per_token": 1.857e-06, "litellm_provider": "databricks", "max_input_tokens": 8192, - "max_tokens": 8192, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21219,6 +23384,8 @@ "databricks/databricks-inkling": { "cache_creation_input_token_cost": 1.00002e-06, "cache_read_input_token_cost": 1.7003e-07, + "deprecation_date": "2026-10-30", + "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", @@ -21229,7 +23396,8 @@ "mode": "chat", "output_cost_per_token": 4.04999e-06, "output_dbu_cost_per_token": 5.7857e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "successor_model": "databricks/databricks-glm-5-3", "supported_modalities": [ "text", "image" @@ -21250,9 +23418,9 @@ "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", + "token_count_framing": 100, "max_input_tokens": 1000000, "max_output_tokens": 1048576, - "max_tokens": 1048576, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference." }, @@ -21271,7 +23439,19 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_priority": 5.25e-06, + "output_cost_per_token_priority": 2.625e-05, + "cache_read_input_token_cost_priority": 5.25e-07, + "cache_creation_input_token_cost_priority": 5.25e-06 + }, + "databricks/kimi-latest": { + "alias_of": "databricks/databricks-kimi-k3" + }, + "databricks/system.ai.kimi-k3": { + "litellm_provider": "databricks", + "mode": "chat", + "token_count_framing": 100 }, "databricks/databricks-llama-4-maverick": { "cache_creation_input_token_cost": 5.0001e-07, @@ -21281,12 +23461,11 @@ "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." }, "mode": "chat", - "output_cost_per_token": 1.5000300000000002e-06, + "output_cost_per_token": 1.50003e-06, "output_dbu_cost_per_token": 2.1429e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true @@ -21294,17 +23473,16 @@ "databricks/databricks-meta-llama-3-1-8b-instruct": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, - "input_cost_per_token": 1.5000999999999998e-07, + "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", - "max_input_tokens": 200000, + "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 4.5003000000000007e-07, + "output_cost_per_token": 4.5003e-07, "output_dbu_cost_per_token": 6.429000000000001e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, @@ -21316,12 +23494,11 @@ "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", - "output_cost_per_token": 1.5000300000000002e-06, + "output_cost_per_token": 1.50003e-06, "output_dbu_cost_per_token": 2.1429e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true @@ -21334,7 +23511,6 @@ "litellm_provider": "databricks", "max_input_tokens": 262144, "max_output_tokens": 25000, - "max_tokens": 25000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, @@ -21352,7 +23528,11 @@ "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false, - "thinking_always_on": true + "thinking_always_on": true, + "input_cost_per_token_priority": 3.85e-07, + "output_cost_per_token_priority": 3.85e-06, + "cache_read_input_token_cost_priority": 3.85e-07, + "cache_creation_input_token_cost_priority": 3.85e-07 }, "databricks/databricks-qwen3-next-80b-a3b-instruct": { "cache_creation_input_token_cost": 1.5001e-07, @@ -21384,7 +23564,6 @@ "input_dbu_cost_per_token": 2.86e-07, "litellm_provider": "databricks", "max_input_tokens": 32768, - "max_tokens": 32768, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, @@ -21395,17 +23574,38 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-openjev-qwen35-4b": { - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 0.0, - "input_cost_per_token": 0.0, + "cache_creation_input_token_cost": 4.2e-08, + "cache_read_input_token_cost": 4.2e-08, + "input_cost_per_token": 4.2e-08, + "input_dbu_cost_per_token": 6e-07, "litellm_provider": "databricks", "metadata": { - "notes": "Pay-per-token Foundation Model API decision endpoint (OpenJev, Qwen 3.5 4B) queried through the System One API. Databricks published no DBU rate for it as of 2026-10-07, so a deployment's model_info prices set the billed cost." + "notes": "Pay-per-token Foundation Model API decision endpoint (OpenJev, Qwen 3.5 4B) queried through the System One API. The serving-endpoints API lists it at 0.6 DBUs per 1M input tokens (input_price on the foundation_model entry, read 2026-10-27); input_cost_per_token is that dbu cost * $0.070, the same conversion as the other databricks rows. Output is free. Databricks publishes no cache rates for it, so cache tokens bill at the input rate." }, "mode": "evaluation", "output_cost_per_token": 0.0, + "output_dbu_cost_per_token": 0.0, "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models" }, + "databricks/databricks-typesafeai-jev-1-14-0": { + "cache_creation_input_token_cost": 4.2e-08, + "cache_read_input_token_cost": 4.2e-08, + "input_cost_per_token": 4.2e-08, + "input_dbu_cost_per_token": 6e-07, + "litellm_provider": "databricks", + "metadata": { + "notes": "TypeSafe AI Jev 1.14.0, provider-hosted by TypeSafe AI and served through Unity Gateway, queried through the System One API. The proprietary pricing page lists 'Jev 1.14' at 0.600 DBU per 1M input tokens; input_cost_per_token is that times $0.070 per DBU. Output is free. No cache rates are published, so cache tokens bill at the input rate." + }, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "output_dbu_cost_per_token": 0.0, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supports_vision": true + }, "databricks/ai_decide": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 0.0, @@ -21425,17 +23625,36 @@ }, "davinci-002": { "deprecation_date": "2026-09-28", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "source": "https://developers.openai.com/api/docs/pricing" }, + "deepgram/aura": { + "input_cost_per_character": 1.5e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0150/1000 characters = $0.000015 per character", + "note": "Aura-1 text-to-speech voices (aura--), pay as you go" + }, + "source": "https://deepgram.com/pricing" + }, + "deepgram/aura-2": { + "input_cost_per_character": 3e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.030/1000 characters = $0.00003 per character", + "note": "Aura-2 text-to-speech voices (aura-2--), pay as you go" + }, + "source": "https://deepgram.com/pricing" + }, "deepgram/base": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", @@ -21857,12 +24076,12 @@ ] }, "deepgram/streaming/nova-3": { - "input_cost_per_second": 8e-05, + "input_cost_per_second": 0.00012833, "litellm_provider": "deepgram", "metadata": { - "calculation": "$0.0048/60 seconds = $0.00008000 per second", + "calculation": "$0.0077/60 seconds = $0.00012833 per second", "note": "Nova-3 monolingual streaming, pay as you go", - "original_pricing_per_minute": 0.0048 + "original_pricing_per_minute": 0.0077 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, @@ -21871,13 +24090,28 @@ "/v1/listen" ] }, + "deepgram/streaming/nova-3-medical": { + "input_cost_per_second": 0.00012833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0077/60 seconds = $0.00012833 per second", + "note": "Nova-3 Medical streaming, launch price from Deepgram's 2025-03-03 announcement. deepgram.com/pricing does not list Nova-3 Medical, and this matches its current Nova-3 monolingual streaming pay as you go rate", + "original_pricing_per_minute": 0.0077 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://www.businesswire.com/news/home/20250303470439/en", + "supported_endpoints": [ + "/v1/listen" + ] + }, "deepgram/streaming/nova-3-multilingual": { - "input_cost_per_second": 9.667e-05, + "input_cost_per_second": 0.00015333, "litellm_provider": "deepgram", "metadata": { - "calculation": "$0.0058/60 seconds = $0.00009667 per second", + "calculation": "$0.0092/60 seconds = $0.00015333 per second", "note": "Nova-3 multilingual (language=multi) streaming, pay as you go", - "original_pricing_per_minute": 0.0058 + "original_pricing_per_minute": 0.0092 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, @@ -22025,7 +24259,6 @@ ] }, "deepinfra/Gryphe/MythoMax-L2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 4e-07, @@ -22037,7 +24270,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-06, @@ -22048,7 +24280,6 @@ "supports_function_calling": true }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 7e-07, @@ -22059,7 +24290,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/QwQ-32B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, @@ -22070,7 +24300,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen2.5-72B-Instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 3.6e-07, @@ -22082,7 +24311,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen2.5-7B-Instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 4e-08, @@ -22092,7 +24320,6 @@ "supports_tool_choice": false }, "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -22104,7 +24331,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-14B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.2e-07, @@ -22116,7 +24342,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.8e-07, @@ -22127,7 +24352,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-08, @@ -22139,7 +24363,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-07, @@ -22150,7 +24373,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-30B-A3B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.2e-07, @@ -22162,7 +24384,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-32B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 8e-08, @@ -22174,7 +24395,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 4e-07, @@ -22185,7 +24405,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-07, @@ -22199,7 +24418,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-08, @@ -22211,7 +24429,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.4e-07, @@ -22222,7 +24439,6 @@ "supports_function_calling": true }, "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, @@ -22232,7 +24448,6 @@ "supports_tool_choice": false }, "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 8.5e-07, @@ -22243,7 +24458,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6.5e-07, @@ -22253,7 +24467,6 @@ "supports_tool_choice": false }, "deepinfra/allenai/olmOCR-7B-0725-FP8": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2.7e-07, @@ -22263,7 +24476,6 @@ "supports_tool_choice": false }, "deepinfra/anthropic/claude-3-7-sonnet-latest": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 3.3e-06, @@ -22275,7 +24487,6 @@ "supports_function_calling": true }, "deepinfra/anthropic/claude-4-opus": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 1.65e-05, @@ -22286,7 +24497,6 @@ "supports_function_calling": true }, "deepinfra/anthropic/claude-4-sonnet": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 3.3e-06, @@ -22297,7 +24507,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 7e-07, @@ -22308,19 +24517,17 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.15e-06, - "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost": 3.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-06, @@ -22331,7 +24538,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -22341,7 +24547,6 @@ "supports_tool_choice": false }, "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.7e-07, @@ -22352,7 +24557,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-06, @@ -22363,7 +24567,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-V3": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 3.2e-07, @@ -22375,7 +24578,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.4e-07, @@ -22389,12 +24591,11 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 9.5e-07, - "cache_read_input_token_cost": 2.16e-07, + "cache_read_input_token_cost": 1.3e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, @@ -22403,7 +24604,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.7e-07, @@ -22415,7 +24615,6 @@ "supports_function_calling": true }, "deepinfra/google/gemini-2.5-flash": { - "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "input_cost_per_token": 3e-07, @@ -22431,7 +24630,6 @@ "supports_audio_input": true }, "deepinfra/google/gemini-2.5-pro": { - "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "input_cost_per_token": 1.25e-06, @@ -22446,7 +24644,6 @@ "supports_audio_input": true }, "deepinfra/google/gemma-3-12b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-08, @@ -22458,7 +24655,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-3-27b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 8e-08, @@ -22470,7 +24666,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-3-4b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-08, @@ -22482,7 +24677,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4.9e-08, @@ -22492,7 +24686,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Llama-3.2-3B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, @@ -22503,7 +24696,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.3e-07, @@ -22514,7 +24706,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -22526,7 +24717,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 2e-07, @@ -22538,7 +24728,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "max_tokens": 327680, "max_input_tokens": 327680, "max_output_tokens": 327680, "input_cost_per_token": 1e-07, @@ -22550,7 +24739,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-Guard-3-8B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5.5e-08, @@ -22560,7 +24748,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Llama-Guard-4-12B": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.8e-07, @@ -22570,7 +24757,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, @@ -22581,7 +24767,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, @@ -22592,7 +24777,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, @@ -22604,7 +24788,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -22615,7 +24798,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, @@ -22627,7 +24809,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/microsoft/WizardLM-2-8x22B": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 4.8e-07, @@ -22637,7 +24818,6 @@ "supports_tool_choice": false }, "deepinfra/microsoft/phi-4": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 7e-08, @@ -22648,10 +24828,9 @@ "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 1.9e-08, + "input_cost_per_token": 2.9e-08, "output_cost_per_token": 3e-08, "litellm_provider": "deepinfra", "mode": "chat", @@ -22660,7 +24839,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-08, @@ -22671,7 +24849,6 @@ "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 7.5e-08, @@ -22682,7 +24859,6 @@ "supports_function_calling": true }, "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 4e-07, @@ -22693,7 +24869,6 @@ "supports_function_calling": true }, "deepinfra/moonshotai/Kimi-K2-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-07, @@ -22704,7 +24879,6 @@ "supports_function_calling": true }, "deepinfra/moonshotai/Kimi-K2-Instruct-0905": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-07, @@ -22716,7 +24890,6 @@ "supports_function_calling": true }, "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6e-07, @@ -22727,7 +24900,6 @@ "supports_function_calling": true }, "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -22739,8 +24911,8 @@ }, "deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning": { "max_input_tokens": 262144, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2e-07, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 1.6e-07, "litellm_provider": "deepinfra", "mode": "chat", "source": "https://deepinfra.com/pricing", @@ -22751,7 +24923,6 @@ "supports_prompt_caching": true }, "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-08, @@ -22762,7 +24933,6 @@ "supports_function_calling": true }, "deepinfra/openai/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3.7e-08, @@ -22774,7 +24944,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/openai/gpt-oss-20b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -22786,7 +24955,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.5": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, @@ -22800,12 +24968,12 @@ "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.8e-08, "deprecation_date": "2026-07-24", + "deprecation_source": "https://api-docs.deepseek.com/updates", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -22828,7 +24996,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07, "supports_assistant_prefill": true, @@ -22843,7 +25010,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.19e-06, "supports_assistant_prefill": true, @@ -22855,12 +25021,12 @@ "deepseek/deepseek-reasoner": { "cache_read_input_token_cost": 2.8e-08, "deprecation_date": "2026-07-24", + "deprecation_source": "https://api-docs.deepseek.com/updates", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -22885,7 +25051,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.1e-06, "supports_assistant_prefill": true, @@ -22900,7 +25065,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 4e-07, "supports_assistant_prefill": true, @@ -22911,11 +25075,11 @@ }, "deepseek.v3-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html", "input_cost_per_token": 5.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html", @@ -22926,19 +25090,22 @@ }, "deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_batches": 3.1e-07, "input_cost_per_token_flex": 3.1e-07, + "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock_converse", - "max_input_tokens": 164000, + "max_input_tokens": 156000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_batches": 9.25e-07, "output_cost_per_token_flex": 9.25e-07, + "output_cost_per_token_priority": 3.2375e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -22948,7 +25115,6 @@ "litellm_provider": "nlp_cloud", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "completion", "output_cost_per_token": 5e-07 }, @@ -22957,7 +25123,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 98304, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, @@ -22971,7 +25136,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, @@ -22985,7 +25149,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 229376, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, @@ -22998,7 +25161,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - standard version with 2560 dimensions" }, @@ -23010,7 +25172,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - large version with 2048 dimensions" }, @@ -23022,7 +25183,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-240915 version with 4096 dimensions" }, @@ -23034,7 +25194,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-250515 version with 2048 dimensions" }, @@ -23046,7 +25205,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-240715 version with 2560 dimensions" }, @@ -23153,13 +25311,17 @@ "notes": "Firecrawl search pricing: $83 for 100,000 credits, 2 credits per 10 results. Cost = ceiling(limit/10) * 2 * $0.00083" } }, + "webiq/search": { + "input_cost_per_query": 0.007, + "litellm_provider": "webiq", + "mode": "search" + }, "perplexity/search": { "input_cost_per_query": 0.005, "litellm_provider": "perplexity", "mode": "search" }, "sail/moonshotai/Kimi-K3": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 2.5e-06, @@ -23181,7 +25343,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/zai-org/GLM-5.3": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 9.8e-07, @@ -23203,7 +25364,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/zai-org/GLM-5.3-Flash": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.1e-07, @@ -23225,7 +25385,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/deepseek-ai/DeepSeek-V4-Pro-0813": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 9.2e-07, @@ -23247,7 +25406,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/deepseek-ai/DeepSeek-V4-Flash-0731": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 9e-08, @@ -23269,17 +25427,16 @@ "source": "https://docs.sailresearch.com/models" }, "sail/deepseek-ai/DeepSeek-V4.1-Flash": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3e-07, "cache_read_input_token_cost": 6e-09, - "input_cost_per_token_balanced": 1.2e-07, - "output_cost_per_token_balanced": 4.8e-07, + "input_cost_per_token_balanced": 7e-08, + "output_cost_per_token_balanced": 2.2e-07, "cache_read_input_token_cost_balanced": 5e-09, - "input_cost_per_token_flex": 8e-08, - "output_cost_per_token_flex": 3e-07, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 1.5e-07, "cache_read_input_token_cost_flex": 4e-09, "litellm_provider": "sail", "mode": "chat", @@ -23291,7 +25448,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/moonshotai/Kimi-K2.6": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-06, @@ -23314,7 +25470,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/google/gemma-4-31B-it": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 4e-07, @@ -23337,7 +25492,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/nvidia/Gemma-4-31B-IT-NVFP4": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.4e-07, @@ -23360,7 +25514,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/google/gemma-4-12B-it": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 3e-07, @@ -23382,7 +25535,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/openai/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6e-08, @@ -23398,7 +25550,6 @@ "source": "https://docs.sailresearch.com/models" }, "sail/Qwen/Qwen3.6-35B-A3B": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-08, @@ -23450,7 +25601,7 @@ } }, "agentcore/search": { - "input_cost_per_query": 0.0, + "input_cost_per_query": 0.007, "litellm_provider": "agentcore", "mode": "search", "metadata": { @@ -23465,6 +25616,11 @@ "notes": "Grounding with Bing Search (G1 SKU): $14 per 1,000 transactions. Tokens for the Foundry model deployment that runs the grounded search are billed separately on that deployment." } }, + "deepseek/search": { + "input_cost_per_query": 0.00075, + "litellm_provider": "deepseek", + "mode": "search" + }, "tinyfish/search": { "input_cost_per_query": 0.0, "litellm_provider": "tinyfish", @@ -23512,27 +25668,118 @@ ] }, "elevenlabs/eleven_v3": { - "input_cost_per_character": 0.00018, + "input_cost_per_character": 8e-05, "litellm_provider": "elevenlabs", "metadata": { - "calculation": "$0.18/1000 characters (Scale plan pricing, 1 credit per character)", + "calculation": "$0.08/1000 characters (API usage pricing, billed in USD per character)", "notes": "ElevenLabs Eleven v3 - most expressive TTS model with 70+ languages and audio tags support" }, "mode": "audio_speech", - "source": "https://elevenlabs.io/pricing", + "source": "https://elevenlabs.io/pricing/api", "supported_endpoints": [ "/v1/audio/speech" ] }, "elevenlabs/eleven_multilingual_v2": { - "input_cost_per_character": 0.00018, + "input_cost_per_character": 8e-05, "litellm_provider": "elevenlabs", "metadata": { - "calculation": "$0.18/1000 characters (Scale plan pricing, 1 credit per character)", + "calculation": "$0.08/1000 characters (API usage pricing, billed in USD per character)", "notes": "ElevenLabs Eleven Multilingual v2 - default TTS model with 29 languages support" }, "mode": "audio_speech", - "source": "https://elevenlabs.io/pricing", + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "elevenlabs/eleven_v4": { + "input_cost_per_character": 8e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.08/1000 characters (API usage pricing, billed in USD per character)", + "notes": "ElevenLabs Eleven v4 - most emotive TTS model with audio tags and 90+ languages" + }, + "mode": "audio_speech", + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "elevenlabs/eleven_v4_turbo": { + "input_cost_per_character": 4e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", + "notes": "ElevenLabs Eleven v4 Turbo - low-latency v4 tuned for real-time and agents" + }, + "mode": "audio_speech", + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "elevenlabs/eleven_v3_conversational": { + "input_cost_per_character": 4e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", + "notes": "ElevenLabs Eleven v3 Conversational - low-latency v3 tuned for realtime conversation" + }, + "mode": "audio_speech", + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "elevenlabs/eleven_flash_v2_5": { + "input_cost_per_character": 4e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", + "notes": "ElevenLabs Eleven Flash v2.5 - low-latency multilingual TTS model" + }, + "mode": "audio_speech", + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "elevenlabs/eleven_flash_v2": { + "input_cost_per_character": 4e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", + "notes": "ElevenLabs Eleven Flash v2 - low-latency English-only TTS model" + }, + "mode": "audio_speech", + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "elevenlabs/eleven_turbo_v2_5": { + "input_cost_per_character": 4e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", + "notes": "ElevenLabs Eleven Turbo v2.5 - multilingual TTS model" + }, + "mode": "audio_speech", + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "elevenlabs/eleven_turbo_v2": { + "input_cost_per_character": 4e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", + "notes": "ElevenLabs Eleven Turbo v2 - English-only TTS model" + }, + "mode": "audio_speech", + "source": "https://elevenlabs.io/pricing/api", "supported_endpoints": [ "/v1/audio/speech" ] @@ -23541,7 +25788,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -23550,7 +25796,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, @@ -23563,7 +25808,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true @@ -23572,7 +25816,6 @@ "input_cost_per_token": 0.0001, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true @@ -23583,7 +25826,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.12e-07, "supports_function_calling": true, @@ -23599,7 +25841,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.84e-07, "supports_function_calling": true, @@ -23615,7 +25856,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 4.2e-06, "output_cost_per_token_flex": 2.1e-06, @@ -23632,7 +25872,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -23651,11 +25890,11 @@ "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, "deprecation_date": "2026-10-15", + "successor_model": "eu.anthropic.claude-haiku-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -23672,14 +25911,17 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -23695,7 +25937,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -23714,7 +25955,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -23734,7 +25974,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -23751,7 +25990,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -23769,7 +26007,12 @@ "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, - "deprecation_date": "2027-01-08" + "deprecation_date": "2027-01-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "token_count_model": { + "model": "anthropic.claude-opus-4-1-20250805-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -23778,7 +26021,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -23801,15 +26043,16 @@ "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "eu.anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -23828,7 +26071,11 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, @@ -23841,11 +26088,12 @@ "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "deprecation_date": "2027-04-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "eu.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -23867,27 +26115,35 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "eu.meta.llama3-2-1b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "input_cost_per_token": 1.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.3e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "eu.meta.llama3-2-3b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "input_cost_per_token": 1.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.9e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, @@ -23896,7 +26152,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.md", @@ -23913,8 +26168,11 @@ }, "fal_ai/fal-ai/flux-pro/v1.1": { "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-pro/v1.1 at $0.04 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.04, + "output_cost_per_pixel": 3.814697265625e-08, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1", "supported_endpoints": [ "/v1/images/generations" ] @@ -23923,14 +26181,18 @@ "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1-ultra", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux/schnell": { "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/schnell at $0.003 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.003, + "output_cost_per_pixel": 2.86102294921875e-09, + "source": "https://fal.ai/models/fal-ai/flux/schnell", "supported_endpoints": [ "/v1/images/generations" ] @@ -23968,6 +26230,9 @@ "video" ] }, + "fal_ai/bytedance/seedance-latest/text-to-video": { + "alias_of": "fal_ai/bytedance/seedance-2.5/text-to-video" + }, "fal_ai/bytedance/seedance-2.5/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", @@ -23986,6 +26251,9 @@ "video" ] }, + "fal_ai/bytedance/seedance-latest/image-to-video": { + "alias_of": "fal_ai/bytedance/seedance-2.5/image-to-video" + }, "fal_ai/bytedance/seedance-2.5/reference-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", @@ -24004,8 +26272,12 @@ "video" ] }, + "fal_ai/bytedance/seedance-latest/reference-to-video": { + "alias_of": "fal_ai/bytedance/seedance-2.5/reference-to-video" + }, "fal_ai/minimax/h3/text-to-video": { "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, "mode": "video_generation", "output_cost_per_second": 0.13, "output_cost_per_second_480p": 0.05, @@ -24115,6 +26387,7 @@ "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/ideogram/v3", "supported_endpoints": [ "/v1/images/generations" ] @@ -24153,8 +26426,11 @@ }, "fal_ai/fal-ai/stable-diffusion-v35-medium": { "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/stable-diffusion-v35-medium at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", - "output_cost_per_image": 0.0398, + "output_cost_per_image": 0.02, + "output_cost_per_pixel": 1.9073486328125e-08, + "source": "https://fal.ai/models/fal-ai/stable-diffusion-v35-medium", "supported_endpoints": [ "/v1/images/generations" ] @@ -24162,7 +26438,8 @@ "fal_ai/fal-ai/nano-banana": { "litellm_provider": "fal_ai", "mode": "image_generation", - "output_cost_per_image": 0.039, + "output_cost_per_image": 0.0398, + "source": "https://fal.ai/models/fal-ai/nano-banana", "supported_endpoints": [ "/v1/images/generations" ] @@ -24170,7 +26447,8 @@ "fal_ai/fal-ai/gemini-25-flash-image": { "litellm_provider": "fal_ai", "mode": "image_generation", - "output_cost_per_image": 0.039, + "output_cost_per_image": 0.0398, + "source": "https://fal.ai/models/fal-ai/gemini-25-flash-image", "supported_endpoints": [ "/v1/images/generations" ] @@ -24206,6 +26484,46 @@ "/v1/images/generations" ] }, + "fal_ai/google/nano-banana-2.1": { + "litellm_provider": "fal_ai", + "metadata": { + "comment": "fal bills this endpoint by tokens and reports the charge in the x-fal-billable-units response header, priced at output_cost_per_billable_unit dollars per unit. The per-image prices are fal's representative costs by the request's resolution field (1K default, 2K, 4K) for a short prompt, used when the header is absent" + }, + "mode": "image_generation", + "output_cost_per_billable_unit": 1.0, + "output_cost_per_image": 0.04, + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.059, + "output_cost_per_image_4K": 0.134, + "source": "https://fal.ai/models/google/nano-banana-2.1", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/google/nano-banana-2.1/edit": { + "litellm_provider": "fal_ai", + "metadata": { + "comment": "fal bills this endpoint by tokens and reports the charge in the x-fal-billable-units response header, priced at output_cost_per_billable_unit dollars per unit. The per-image prices are fal's representative costs by the request's resolution field (1K default, 2K, 4K) for a short prompt and two 1K input images, used when the header is absent" + }, + "mode": "image_generation", + "output_cost_per_billable_unit": 1.0, + "output_cost_per_image": 0.044, + "output_cost_per_image_1K": 0.044, + "output_cost_per_image_2K": 0.063, + "output_cost_per_image_4K": 0.138, + "source": "https://fal.ai/models/google/nano-banana-2.1/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/google/nano-banana-latest": { + "alias_of": "fal_ai/google/nano-banana-2.1" + }, + "fal_ai/google/nano-banana-latest/edit": { + "alias_of": "fal_ai/google/nano-banana-2.1/edit" + }, "fal_ai/openai/gpt-image-2": { "litellm_provider": "fal_ai", "metadata": { @@ -26101,9 +28419,7 @@ }, "fal_ai/fal-ai/flux/dev": { "litellm_provider": "fal_ai", - "metadata": { - "notes": "fal bills FLUX.1 [dev] at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price is the fallback when dimensions are unavailable" - }, + "metadata": {"notes":"fal bills fal-ai/flux/dev at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, @@ -26135,16 +28451,16 @@ }, "fal_ai/fal-ai/flux-lora-depth": { "litellm_provider": "fal_ai", - "metadata": { - "notes": "fal bills fal-ai/flux-lora-depth at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries" - }, + "metadata": {"notes":"fal bills fal-ai/flux-lora-depth at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-lora-depth", "supported_endpoints": [ - "/v1/images/edits" - ] + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true }, "fal_ai/fal-ai/moondream3-preview/query": { "input_cost_per_token": 4e-07, @@ -26162,14 +28478,12 @@ "litellm_provider": "featherless_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat" }, "featherless_ai/featherless-ai/Qwerky-QwQ-32B": { "litellm_provider": "featherless_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat" }, "fireworks-ai-4.1b-to-16b": { @@ -26217,7 +28531,6 @@ "input_cost_per_token": 1.6e-08, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -26227,7 +28540,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/pricing", @@ -26238,9 +28550,8 @@ "fireworks_ai/accounts/fireworks/models/deepseek-r1": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 163840, "max_output_tokens": 20480, - "max_tokens": 20480, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://fireworks.ai/pricing", @@ -26250,9 +28561,8 @@ "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 160000, + "max_input_tokens": 163840, "max_output_tokens": 160000, - "max_tokens": 160000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://fireworks.ai/pricing", @@ -26262,9 +28572,8 @@ "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { "input_cost_per_token": 5.5e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 163840, "max_output_tokens": 20480, - "max_tokens": 20480, "mode": "chat", "output_cost_per_token": 2.19e-06, "source": "https://fireworks.ai/pricing", @@ -26274,9 +28583,8 @@ "fireworks_ai/accounts/fireworks/models/deepseek-v3": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -26288,7 +28596,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324", @@ -26300,7 +28607,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/pricing", @@ -26313,7 +28619,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/pricing", @@ -26326,7 +28631,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/models/fireworks/deepseek-v3p2", @@ -26337,14 +28641,16 @@ }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-08-14", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1.4e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://docs.fireworks.ai/serverless/pricing", + "successor_model": "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -26360,7 +28666,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.96e-06, "output_cost_per_token_priority": 4.95e-06, @@ -26380,7 +28685,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.96e-06, "output_cost_per_token_priority": 4.95e-06, @@ -26396,7 +28700,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -26407,9 +28710,8 @@ "fireworks_ai/accounts/fireworks/models/glm-4p5": { "input_cost_per_token": 5.5e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 96000, - "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 2.19e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p5", @@ -26421,9 +28723,8 @@ "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { "input_cost_per_token": 2.2e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 96000, - "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://artificialanalysis.ai/models/glm-4-5-air", @@ -26436,9 +28737,8 @@ "input_cost_per_token": 5.5e-07, "output_cost_per_token": 2.19e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "source": "https://fireworks.ai/pricing", "supports_function_calling": true, @@ -26450,9 +28750,8 @@ "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p7", @@ -26465,9 +28764,8 @@ "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -26481,12 +28779,12 @@ "cache_read_input_token_cost": 1.4e-07, "cache_read_input_token_cost_priority": 1.75e-07, "deprecation_date": "2026-09-25", + "successor_model": "fireworks_ai/accounts/fireworks/models/glm-5p3", "input_cost_per_token": 1.4e-06, "input_cost_per_token_priority": 1.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, @@ -26500,16 +28798,17 @@ "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { "cache_read_input_token_cost": 1.5e-08, "cache_read_input_token_cost_priority": 1.8e-08, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 7.2e-07, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -26522,7 +28821,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -26537,7 +28835,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct", @@ -26550,7 +28847,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://app.fireworks.ai/models/fireworks/kimi-k2-instruct-0905", @@ -26563,7 +28859,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://fireworks.ai/pricing", @@ -26578,7 +28873,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -26595,7 +28889,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -26615,7 +28908,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -26629,9 +28921,8 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -26642,9 +28933,8 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", @@ -26655,9 +28945,8 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://fireworks.ai/pricing", @@ -26669,9 +28958,8 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", @@ -26682,9 +28970,8 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", @@ -26695,9 +28982,8 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -26710,7 +28996,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://fireworks.ai/pricing", @@ -26722,7 +29007,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://fireworks.ai/pricing", @@ -26733,9 +29017,8 @@ "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 204800, + "max_input_tokens": 196608, "max_output_tokens": 204800, - "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", @@ -26751,23 +29034,42 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.8e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/minimax-latest": { + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_priority": 9e-08, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 4.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 512000, + "max_output_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.8e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/minimax-latest": { + "alias_of": "fireworks_ai/accounts/fireworks/models/minimax-m3" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { "input_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/pricing", @@ -26780,7 +29082,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -26793,7 +29094,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -26806,7 +29106,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -26816,14 +29115,16 @@ }, "fireworks_ai/deepseek-v4-flash": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-08-14", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1.4e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://docs.fireworks.ai/serverless/pricing", + "successor_model": "fireworks_ai/deepseek-v4-flash-0731", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -26834,9 +29135,8 @@ "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p7", @@ -26849,9 +29149,8 @@ "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -26867,7 +29166,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -26881,12 +29179,12 @@ "cache_read_input_token_cost": 1.4e-07, "cache_read_input_token_cost_priority": 1.75e-07, "deprecation_date": "2026-09-25", + "successor_model": "fireworks_ai/glm-5p3", "input_cost_per_token": 1.4e-06, "input_cost_per_token_priority": 1.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, @@ -26900,16 +29198,17 @@ "fireworks_ai/gpt-oss-120b": { "cache_read_input_token_cost": 1.5e-08, "cache_read_input_token_cost_priority": 1.8e-08, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 7.2e-07, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -26922,7 +29221,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -26938,7 +29236,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -26955,7 +29252,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -26969,14 +29265,15 @@ "fireworks_ai/kimi-k2p6-fast": { "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-08-27", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/kimi-k2p6", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -26992,7 +29289,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -27006,14 +29302,15 @@ "fireworks_ai/kimi-k2p7-code-fast": { "cache_read_input_token_cost": 3.8e-07, "deprecation_date": "2026-08-27", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 1.9e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/kimi-k2p7-code", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -27024,9 +29321,8 @@ "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 204800, + "max_input_tokens": 196608, "max_output_tokens": 204800, - "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", @@ -27042,7 +29338,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.8e-06, @@ -27051,7 +29346,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "fireworks_ai/qwen3p7-plus": { "cache_read_input_token_cost": 8e-08, @@ -27059,7 +29354,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -27073,7 +29367,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -27082,7 +29375,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -27091,7 +29383,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -27100,7 +29391,6 @@ "input_cost_per_token": 1.6e-08, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -27109,7 +29399,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 3e-08, @@ -27137,7 +29426,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "input_cost_per_token": 1.26e-06, "output_cost_per_token": 3.96e-06, "cache_read_input_token_cost": 2.34e-07, @@ -27165,7 +29453,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 4e-07, "supports_prompt_caching": false, @@ -27188,7 +29475,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, @@ -27211,59 +29497,10 @@ "comment": "Open flagship GLM for long-horizon coding agents and million-token context work", "source": "https://api.friendli.ai/serverless/v1/models" }, - "friendliai/deepseek-ai/DeepSeek-V3.2": { - "litellm_provider": "friendliai", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "cache_read_input_token_cost": 2.5e-07, - "supports_prompt_caching": true, - "supports_reasoning": true, - "reasoning_effort_levels": [], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_image_input": false, - "supports_video_input": false, - "mode": "chat", - "comment": "DeepSeek chat model for instruction following, coding, and analysis", - "source": "https://api.friendli.ai/serverless/v1/models" - }, - "friendliai/MiniMaxAI/MiniMax-M2.5": { - "litellm_provider": "friendliai", - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "max_tokens": 196608, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 6e-08, - "supports_prompt_caching": true, - "supports_reasoning": true, - "reasoning_effort_levels": [], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_image_input": false, - "supports_video_input": false, - "mode": "chat", - "comment": "Prior MiniMax coding model for agent workflows, office edits, and automation", - "source": "https://api.friendli.ai/serverless/v1/models" - }, "friendliai/zai-org/GLM-5.1": { "litellm_provider": "friendliai", "max_input_tokens": 202752, "max_output_tokens": 202752, - "max_tokens": 202752, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, @@ -27281,29 +29518,32 @@ "supports_video_input": false, "mode": "chat", "comment": "Strong GLM coding model for agentic engineering, terminals, and repository generation", - "source": "https://api.friendli.ai/serverless/v1/models" + "source": "https://api.friendli.ai/serverless/v1/models", + "deprecation_date": "2026-11-20" }, "ft:babbage-002": { - "deprecation_date": "2026-10-23", + "deprecation_date": "2026-09-28", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1.6e-06, "input_cost_per_token_batches": 8e-07, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 9e-07, "source": "https://developers.openai.com/api/docs/pricing" }, "ft:davinci-002": { - "deprecation_date": "2026-10-23", + "deprecation_date": "2026-09-28", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1.2e-05, "input_cost_per_token_batches": 6e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, @@ -27311,14 +29551,16 @@ }, "ft:gpt-3.5-turbo": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_system_messages": true, @@ -27326,49 +29568,57 @@ }, "ft:gpt-3.5-turbo-0125": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, + "fedramp_uplift_multiplier": 1.1, "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-3.5-turbo-0613": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "ft:gpt-3.5-turbo", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, + "fedramp_uplift_multiplier": 1.1, "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-3.5-turbo-1106": { - "deprecation_date": "2026-10-23", + "deprecation_date": "2026-09-28", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, + "fedramp_uplift_multiplier": 1.1, "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-4-0613": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 3e-05, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, + "fedramp_uplift_multiplier": 1.1, "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", "supports_function_calling": true, "supports_system_messages": true, @@ -27377,14 +29627,17 @@ "ft:gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.875e-06, "cache_read_input_token_cost_batches": 9e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 3.75e-06, "input_cost_per_token_batches": 2.225e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1.25e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -27398,13 +29651,16 @@ }, "ft:gpt-4o-2024-11-20": { "cache_creation_input_token_cost": 1.875e-06, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 3.75e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-05, + "fedramp_uplift_multiplier": 1.1, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -27416,14 +29672,17 @@ "ft:gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 6e-07, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -27437,14 +29696,17 @@ "ft:gpt-4.1-2025-04-14": { "cache_read_input_token_cost": 7.5e-07, "cache_read_input_token_cost_batches": 5e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.2e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 6e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -27457,14 +29719,17 @@ "ft:gpt-4.1-mini-2025-04-14": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 8e-07, "input_cost_per_token_batches": 4e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.2e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1.6e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -27478,14 +29743,16 @@ "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 2.5e-08, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-luna", "input_cost_per_token": 2e-07, "input_cost_per_token_batches": 1e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 4e-07, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -27499,14 +29766,16 @@ "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_batches": 5e-07, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 4e-06, "input_cost_per_token_batches": 2e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 1.6e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 8e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -27518,20 +29787,38 @@ }, "gemini-2.5-flash": { "cache_read_input_audio_token_cost": 1e-07, - "deprecation_date": "2026-10-20", + "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_flex": 3e-08, "cache_read_input_token_cost_priority": 5.4e-08, + "deprecation_date": "2026-10-20", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_above_200k_tokens": 3e-07, + "input_cost_per_audio_token_above_200k_tokens_batches": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_flex": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_priority": 1.8e-06, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_audio_token_flex": 5e-07, + "input_cost_per_audio_token_priority": 1.8e-06, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, + "search_free_requests": {"count":1500,"period":"day","shared_group":"gemini-2-flash"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -27548,6 +29835,7 @@ ], "supports_audio_output": false, "supports_function_calling": true, + "supports_image_size": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -27557,25 +29845,12 @@ "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "input_cost_per_audio_token_batches": 5e-07, - "input_cost_per_token_batches": 1.5e-07, - "input_cost_per_token_flex": 1.5e-07, - "input_cost_per_token_priority": 5.4e-07, - "input_cost_per_audio_token_priority": 1.8e-06, - "output_cost_per_token_batches": 1.25e-06, - "output_cost_per_token_flex": 1.25e-06, - "output_cost_per_token_priority": 4.5e-06, - "supports_image_size": false + "supports_web_search": true }, "gemini-2.5-flash-image": { "deprecation_date": "2027-03-15", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "gemini-3.1-flash-lite-image", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, @@ -27583,10 +29858,10 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, @@ -27630,7 +29905,6 @@ "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.6e-07, - "deprecation_date": "2027-05-28", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, @@ -27641,16 +29915,19 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, + "output_cost_per_image_token_batches": 6e-05, + "output_cost_per_image_token_priority": 0.000216, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27672,11 +29949,6 @@ "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, "web_search_billing_unit": "per_query" }, "gemini-3-pro-image-preview": { @@ -27694,16 +29966,17 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, + "output_cost_per_image_token_batches": 6e-05, + "output_cost_per_image_token_priority": 0.000216, "output_cost_per_token": 1.2e-05, "output_cost_per_token_priority": 2.16e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", @@ -27729,6 +30002,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image": { @@ -27736,23 +30010,25 @@ "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, "cache_read_input_token_cost_priority": 9e-08, - "deprecation_date": "2027-05-28", "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 65536, + "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, + "output_cost_per_image_token_batches": 3e-05, + "output_cost_per_image_token_priority": 0.000108, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.4e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27774,11 +30050,6 @@ "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image-preview": { @@ -27790,13 +30061,14 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, + "output_cost_per_image_token_batches": 3e-05, + "output_cost_per_image_token_priority": 0.000108, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", @@ -27822,6 +30094,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-lite-image": { @@ -27829,7 +30102,6 @@ "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, - "deprecation_date": "2027-06-28", "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, @@ -27838,10 +30110,11 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, + "output_cost_per_image_token_priority": 5.4e-05, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, @@ -27878,7 +30151,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, @@ -27917,33 +30189,45 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "gemini-3.1-flash-lite": { "cache_read_input_audio_token_cost": 5e-08, - "deprecation_date": "2027-05-07", + "cache_read_input_audio_token_cost_batches": 2.5e-08, + "cache_read_input_audio_token_cost_flex": 2.5e-08, + "cache_read_input_audio_token_cost_priority": 9e-08, "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 5e-07, + "input_cost_per_audio_token_above_200k_tokens": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_batches": 2.5e-07, + "input_cost_per_audio_token_above_200k_tokens_flex": 2.5e-07, + "input_cost_per_audio_token_above_200k_tokens_priority": 9e-07, + "input_cost_per_audio_token_batches": 2.5e-07, + "input_cost_per_audio_token_flex": 2.5e-07, + "input_cost_per_audio_token_priority": 9e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, - "input_cost_per_audio_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "gemini-3.5-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -27961,6 +30245,7 @@ "supports_audio_input": true, "supports_audio_output": false, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -27972,22 +30257,14 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "web_search_billing_unit": "per_query" }, "gemini-3.5-flash-lite": { - "deprecation_date": "2027-07-21", "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_batches": 1.5e-08, "cache_read_input_token_cost_flex": 1.5e-08, "cache_read_input_token_cost_priority": 5.4e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, @@ -27995,13 +30272,14 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_flex": 1.25e-06, "output_cost_per_token_priority": 4.5e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -28019,26 +30297,22 @@ ], "supports_audio_input": true, "supports_audio_output": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "web_search_billing_unit": "per_query" }, "deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, @@ -28049,7 +30323,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -28078,20 +30351,38 @@ }, "gemini-2.5-flash-lite": { "cache_read_input_audio_token_cost": 3e-08, - "deprecation_date": "2026-10-20", + "cache_read_input_audio_token_cost_priority": 5.4e-08, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_flex": 1e-08, "cache_read_input_token_cost_priority": 1.8e-08, + "deprecation_date": "2026-10-20", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token": 3e-07, + "input_cost_per_audio_token_above_200k_tokens": 3e-07, + "input_cost_per_audio_token_above_200k_tokens_batches": 5e-08, + "input_cost_per_audio_token_above_200k_tokens_flex": 5e-08, + "input_cost_per_audio_token_above_200k_tokens_priority": 5.4e-07, + "input_cost_per_audio_token_batches": 5e-08, + "input_cost_per_audio_token_flex": 5e-08, + "input_cost_per_audio_token_priority": 5.4e-07, "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_flex": 2e-07, + "output_cost_per_token_priority": 7.2e-07, + "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, + "search_free_requests": {"count":1500,"period":"day","shared_group":"gemini-2-flash"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -28108,6 +30399,7 @@ ], "supports_audio_output": false, "supports_function_calling": true, + "supports_image_size": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -28117,22 +30409,7 @@ "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "input_cost_per_audio_token_batches": 5e-08, - "input_cost_per_token_batches": 5e-08, - "input_cost_per_token_flex": 5e-08, - "input_cost_per_token_priority": 1.8e-07, - "input_cost_per_audio_token_priority": 5.4e-07, - "output_cost_per_token_batches": 2e-07, - "output_cost_per_token_flex": 2e-07, - "output_cost_per_token_priority": 7.2e-07, - "supports_image_size": false + "supports_web_search": true }, "gemini-2.5-flash-lite-preview-09-2025": { "cache_read_input_token_cost": 1e-08, @@ -28141,7 +30418,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, @@ -28177,6 +30453,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, @@ -28187,7 +30464,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -28223,17 +30499,19 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, "gemini-live-2.5-flash-native-audio": { "deprecation_date": "2026-12-13", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -28279,7 +30557,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -28323,7 +30600,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -28363,23 +30639,39 @@ "gemini_native_audio": true }, "gemini-2.5-pro": { - "deprecation_date": "2026-10-20", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-07, "cache_read_input_token_cost_flex": 1.25e-07, "cache_read_input_token_cost_priority": 2.25e-07, + "deprecation_date": "2026-10-20", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 1.25e-06, + "input_cost_per_token_above_200k_tokens_flex": 1.25e-06, + "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_flex": 6.25e-07, + "input_cost_per_token_priority": 2.25e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_token_above_200k_tokens_batches": 7.5e-06, + "output_cost_per_token_above_200k_tokens_flex": 7.5e-06, + "output_cost_per_token_above_200k_tokens_priority": 2.7e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 1.8e-05, + "prompt_cache_min_tokens": 2048.0, + "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, + "search_free_requests": {"count":10000,"period":"day","shared_group":"gemini-2.5-pro"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -28397,46 +30689,44 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "prompt_cache_min_tokens": 2048, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, - "input_cost_per_token_batches": 6.25e-07, - "input_cost_per_token_flex": 6.25e-07, - "input_cost_per_token_priority": 2.25e-06, - "output_cost_per_token_above_200k_tokens_priority": 2.7e-05, - "output_cost_per_token_batches": 5e-06, - "output_cost_per_token_flex": 5e-06, - "output_cost_per_token_priority": 1.8e-05 + "supports_web_search": true }, "gemini-3.1-pro-preview": { - "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_above_200k_tokens_flex": 2e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", + "output_cost_per_image": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, + "output_cost_per_token_above_200k_tokens_batches": 9e-06, + "output_cost_per_token_above_200k_tokens_flex": 9e-06, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, - "output_cost_per_image": 0.00012, + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -28454,46 +30744,29 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_url_context": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 3.6e-06, - "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, - "output_cost_per_token_priority": 2.16e-05, - "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, - "cache_read_input_token_cost_priority": 3.6e-07, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, - "cache_read_input_token_cost_flex": 2e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "web_search_billing_unit": "per_query" }, "gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, @@ -28532,20 +30805,19 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3-pro-preview": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, @@ -28588,20 +30860,37 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, + "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 5e-08, - "cache_read_input_token_cost_flex": 5e-08, - "input_cost_per_token": 5e-07, + "cache_read_input_token_cost_priority": 9e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_above_200k_tokens": 1e-06, + "input_cost_per_audio_token_above_200k_tokens_batches": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_flex": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_priority": 1.8e-06, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_audio_token_flex": 5e-07, + "input_cost_per_audio_token_priority": 1.8e-06, + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.4e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -28618,7 +30907,9 @@ "text" ], "supports_audio_input": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -28628,40 +30919,35 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 9e-07, - "input_cost_per_audio_token_priority": 1.8e-06, - "output_cost_per_token_priority": 5.4e-06, - "cache_read_input_token_cost_priority": 9e-08, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 5e-07, - "input_cost_per_token_batches": 2.5e-07, - "input_cost_per_token_flex": 2.5e-07, - "output_cost_per_token_batches": 1.5e-06, - "output_cost_per_token_flex": 1.5e-06 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.5-flash": { - "prompt_cache_min_tokens": 4096, - "deprecation_date": "2027-05-19", "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, - "input_cost_per_token": 1.5e-06, + "cache_read_input_token_cost_flex": 7.5e-08, + "cache_read_input_token_cost_priority": 2.7e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1.5e-06, + "input_cost_per_audio_token_priority": 2.7e-06, + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_flex": 7.5e-07, + "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, + "output_cost_per_token_batches": 4.5e-06, + "output_cost_per_token_flex": 4.5e-06, + "output_cost_per_token_priority": 1.62e-05, + "prompt_cache_min_tokens": 4096.0, "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "vertex_ai/gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -28677,7 +30963,9 @@ "text" ], "supports_audio_input": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -28689,25 +30977,72 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "vertex_ai/gemini-3.6-flash": { + "prompt_cache_min_tokens": 4096, + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "input_cost_per_token": 7.5e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "regional_endpoint_uplift_multiplier": 1.1, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, "supports_native_streaming": true, - "input_cost_per_token_priority": 2.7e-06, - "input_cost_per_audio_token_priority": 2.7e-06, - "output_cost_per_token_priority": 1.62e-05, - "cache_read_input_token_cost_priority": 2.7e-07, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_priority": 6.75e-06, + "cache_read_input_token_cost_priority": 1.35e-07, + "deprecation_date": "2026-11-19", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/gemini-3.8-flash", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_token_batches": 7.5e-07, - "output_cost_per_token_batches": 4.5e-06, - "input_cost_per_token_flex": 7.5e-07, - "output_cost_per_token_flex": 4.5e-06, - "cache_read_input_token_cost_flex": 7.5e-08 + "google_maps_grounding_cost_per_query": 0.014 }, - "vertex_ai/gemini-3.6-flash": { + "vertex_ai/gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, @@ -28718,66 +31053,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_reasoning_token": 3.75e-06, - "output_cost_per_token": 3.75e-06, - "output_cost_per_token_batches": 1.875e-06, - "output_cost_per_token_flex": 1.875e-06, - "regional_endpoint_uplift_multiplier": 1.1, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 1.35e-06, - "output_cost_per_token_priority": 6.75e-06, - "cache_read_input_token_cost_priority": 1.35e-07, - "deprecation_date": "2026-11-19", - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 - }, - "vertex_ai/gemini-3.7-flash": { - "prompt_cache_min_tokens": 4096, - "cache_read_input_token_cost": 7.5e-08, - "cache_read_input_token_cost_batches": 3.75e-08, - "cache_read_input_token_cost_flex": 3.75e-08, - "input_cost_per_token": 7.5e-07, - "input_cost_per_token_batches": 3.75e-07, - "input_cost_per_token_flex": 3.75e-07, - "litellm_provider": "vertex_ai", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -28800,6 +31075,7 @@ "text" ], "supports_audio_input": true, + "supports_computer_use": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -28807,6 +31083,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -28818,32 +31095,40 @@ "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, "deprecation_date": "2027-01-28", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/gemini-3.8-flash", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3.8-flash": { - "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096.0, "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -28860,30 +31145,23 @@ "text" ], "supports_audio_input": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 1.35e-06, - "output_cost_per_token_priority": 6.75e-06, - "cache_read_input_token_cost_priority": 1.35e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.8-flash-cyber": { "cache_read_input_token_cost": 1.5e-07, @@ -28897,7 +31175,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 7.5e-06, "output_cost_per_token": 7.5e-06, @@ -28926,6 +31203,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_url_context": false, @@ -28935,6 +31213,7 @@ "supports_native_streaming": true }, "vertex_ai/gemini-3.8-live": { + "gemini_audio_only_live": true, "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, @@ -28943,10 +31222,10 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, + "output_cost_per_video_token": 1e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/vertex_ai/live", @@ -28967,27 +31246,38 @@ "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, - "supports_web_search": true, - "gemini_audio_only_live": true, - "output_cost_per_video_token": 1e-06 + "supports_web_search": true }, "vertex_ai/gemini-3.1-pro-preview": { - "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_above_200k_tokens_flex": 2e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", + "output_cost_per_image": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, + "output_cost_per_token_above_200k_tokens_batches": 9e-06, + "output_cost_per_token_above_200k_tokens_flex": 9e-06, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, - "output_cost_per_image": 0.00012, + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -29005,46 +31295,29 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_url_context": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 3.6e-06, - "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, - "output_cost_per_token_priority": 2.16e-05, - "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, - "cache_read_input_token_cost_priority": 3.6e-07, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, - "cache_read_input_token_cost_flex": 2e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, @@ -29089,6 +31362,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29100,7 +31374,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, @@ -29133,7 +31406,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_reasoning_token": 2.5e-06, @@ -29171,7 +31443,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 5e-06, "output_cost_per_token": 5e-06, @@ -29218,7 +31489,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, @@ -29238,11 +31508,12 @@ }, "gemini-embedding-001": { "deprecation_date": "2028-05-20", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "gemini-embedding-2", "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -29259,11 +31530,11 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_embedding_image_input": true, "uses_embed_content": true }, "gemini-embedding-2": { @@ -29277,11 +31548,11 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supports_embedding_image_input": true, "supports_multimodal": true, "uses_embed_content": true }, @@ -29296,11 +31567,11 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_embedding_image_input": true, "supports_multimodal": true, "uses_embed_content": true }, @@ -29315,11 +31586,11 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supports_embedding_image_input": true, "supports_multimodal": true, "uses_embed_content": true }, @@ -29329,7 +31600,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -29338,16 +31608,18 @@ }, "gemini/gemini-embedding-001": { "deprecation_date": "2028-05-14", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-embedding-2", "input_cost_per_token": 1.5e-07, "litellm_provider": "gemini", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions", - "tpm": 10000000 + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "tpm": 10000000, + "input_cost_per_token_batches": 7.5e-08 }, "gemini/gemini-embedding-2": { "input_cost_per_audio_token": 6.5e-06, @@ -29360,19 +31632,21 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "gemini", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_audio_input": true, + "supports_embedding_image_input": true, "supports_multimodal": true, "supports_vision": true, "tpm": 10000000 }, "gemini/gemini-3-pro-image-preview": { "deprecation_date": "2026-06-25", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3-pro-image", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -29381,7 +31655,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -29416,17 +31689,19 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "supports_reasoning": false }, "gemini/gemini-3.1-flash-image-preview": { "deprecation_date": "2026-06-25", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-nano-banana-2.1", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_image_token": 6e-05, @@ -29460,6 +31735,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-lite-preview": { @@ -29469,6 +31745,8 @@ "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2026-05-25", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.1-flash-lite", "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, @@ -29477,7 +31755,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, @@ -29521,11 +31798,14 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 }, "gemini/gemini-embedding-2-preview": { + "deprecation_date": "2026-11-06", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "input_cost_per_audio_token": 6.5e-06, "input_cost_per_audio_token_batches": 3.25e-06, "input_cost_per_image_token": 4.5e-07, @@ -29536,13 +31816,14 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "gemini", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", + "successor_model": "gemini/gemini-embedding-2", "supports_audio_input": true, + "supports_embedding_image_input": true, "supports_multimodal": true, "supports_vision": true, "tpm": 10000000 @@ -29553,7 +31834,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "rpm": 1000, @@ -29590,7 +31870,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "rpm": 1000, @@ -29623,16 +31902,22 @@ }, "gemini/gemini-2.5-flash": { "cache_read_input_audio_token_cost": 1e-07, + "cache_read_input_audio_token_cost_batches": 1e-07, + "cache_read_input_audio_token_cost_flex": 1e-07, + "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_batches": 3e-08, "cache_read_input_token_cost_flex": 3e-08, "cache_read_input_token_cost_priority": 5.4e-08, + "deprecation_date": "2026-12-01", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.5-flash-lite", "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_flex": 5e-07, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -29670,6 +31955,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_audio_token_priority": 1.8e-06, @@ -29685,6 +31971,8 @@ "gemini/gemini-2.5-flash-image": { "cache_read_input_token_cost": 3e-08, "deprecation_date": "2027-03-15", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.1-flash-lite-image", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, @@ -29694,12 +31982,16 @@ "supports_reasoning": false, "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, + "output_cost_per_image_token_priority": 5.4e-05, "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ @@ -29746,7 +32038,6 @@ "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -29782,6 +32073,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "supports_reasoning": true }, @@ -29794,7 +32086,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -29837,7 +32128,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_image_token": 6e-05, @@ -29846,7 +32136,9 @@ "output_cost_per_token_batches": 1.5e-06, "rpm": 1000.0, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-nano-banana-2.1", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", @@ -29878,10 +32170,10 @@ "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "rpm": 1000, @@ -29911,13 +32203,14 @@ }, "gemini/deep-research-pro-preview-12-2025": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/deep-research-preview-04-2026", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, @@ -29949,16 +32242,19 @@ }, "gemini/gemini-2.5-flash-lite": { "cache_read_input_audio_token_cost": 3e-08, + "cache_read_input_audio_token_cost_batches": 3e-08, + "cache_read_input_audio_token_cost_flex": 3e-08, + "cache_read_input_audio_token_cost_priority": 5.4e-08, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_flex": 1e-08, "cache_read_input_token_cost_priority": 1.8e-08, "input_cost_per_audio_token": 3e-07, + "input_cost_per_audio_token_flex": 1.5e-07, "input_cost_per_token": 1e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, @@ -29996,6 +32292,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 1.5e-07, "input_cost_per_audio_token_priority": 5.4e-07, @@ -30010,11 +32307,11 @@ }, "gemini/gemini-flash-latest": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "input_cost_per_token": 7.5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -30069,11 +32366,11 @@ }, "gemini/gemini-flash-lite-latest": { "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_batches": 1.5e-08, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -30127,12 +32424,13 @@ }, "gemini/gemini-2.5-flash-preview-tts": { "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-flash-tts", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, @@ -30162,7 +32460,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, @@ -30201,21 +32498,32 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, - "supports_url_context": true + "supports_url_context": true, + "cache_read_input_token_cost_above_200k_tokens_batches": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens_flex": 2.5e-07, + "deprecation_date": "2026-12-01", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-flash", + "input_cost_per_token_above_200k_tokens_batches": 1.25e-06, + "input_cost_per_token_above_200k_tokens_flex": 1.25e-06, + "output_cost_per_token_above_200k_tokens_batches": 7.5e-06, + "output_cost_per_token_above_200k_tokens_flex": 7.5e-06 }, "gemini/gemini-2.5-computer-use-preview-10-2025": { "deprecation_date": "2026-07-28", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-flash", "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "gemini", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, @@ -30241,12 +32549,18 @@ }, "gemini/gemini-3.1-flash-lite": { "cache_read_input_audio_token_cost": 5e-08, + "cache_read_input_audio_token_cost_batches": 2.5e-08, + "cache_read_input_audio_token_cost_flex": 2.5e-08, + "cache_read_input_audio_token_cost_priority": 9e-08, "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2027-05-07", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.5-flash-lite", "input_cost_per_audio_token": 5e-07, + "input_cost_per_audio_token_flex": 2.5e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, @@ -30254,7 +32568,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, @@ -30298,6 +32611,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07, @@ -30305,7 +32619,7 @@ }, "gemini/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, - "cache_read_input_token_cost_batches": 2e-08, + "cache_read_input_token_cost_batches": 1.5e-08, "cache_read_input_token_cost_flex": 2e-08, "cache_read_input_token_cost_priority": 5e-08, "input_cost_per_token": 3e-07, @@ -30315,7 +32629,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -30346,6 +32659,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -30359,25 +32673,30 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "supports_computer_use": true }, "gemini/gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, + "cache_read_input_audio_token_cost_batches": 1e-07, + "cache_read_input_audio_token_cost_flex": 1e-07, + "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 5e-08, "cache_read_input_token_cost_flex": 5e-08, "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_flex": 5e-07, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -30415,6 +32734,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 5e-07, @@ -30422,7 +32742,9 @@ "input_cost_per_token_flex": 2.5e-07, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, - "supports_audio_input": true + "successor_model": "gemini/gemini-3.6-flash", + "supports_audio_input": true, + "supports_computer_use": true }, "gemini/gemini-3.5-flash": { "prompt_cache_min_tokens": 4096, @@ -30433,12 +32755,11 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -30478,13 +32799,15 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, "output_cost_per_token_batches": 4.5e-06, "input_cost_per_token_flex": 7.5e-07, "output_cost_per_token_flex": 4.5e-06, - "cache_read_input_token_cost_flex": 8e-08 + "cache_read_input_token_cost_flex": 8e-08, + "successor_model": "gemini/gemini-3.6-flash" }, "gemini/gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, @@ -30497,7 +32820,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -30527,6 +32849,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -30543,6 +32866,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -30557,14 +32881,13 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -30588,6 +32911,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -30604,8 +32928,10 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "successor_model": "gemini/gemini-3.8-flash" }, "gemini/gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, @@ -30618,7 +32944,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -30649,6 +32974,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -30665,8 +32991,10 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "supports_computer_use": true }, "gemini/gemini-omni-flash-preview": { "input_cost_per_audio_token": 1.5e-06, @@ -30674,13 +33002,12 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_endpoints": [ "/v1beta/interactions" ], @@ -30700,7 +33027,9 @@ "supports_video_input": true, "supports_vision": true, "tpm": 800000, - "deprecation_date": "2026-10-22" + "deprecation_date": "2026-10-22", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-omni-1.2-flash" }, "gemini/gemini-3.1-pro-preview": { "prompt_cache_min_tokens": 4096, @@ -30712,7 +33041,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, @@ -30760,10 +33088,17 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "output_cost_per_token_flex": 6e-06, + "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_flex": 4e-07, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_above_200k_tokens_flex": 2e-06, + "output_cost_per_token_above_200k_tokens_batches": 9e-06, + "output_cost_per_token_above_200k_tokens_flex": 9e-06 }, "gemini/gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, @@ -30775,7 +33110,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, @@ -30823,24 +33157,47 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "output_cost_per_token_flex": 6e-06, + "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_flex": 4e-07, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_above_200k_tokens_flex": 2e-06, + "output_cost_per_token_above_200k_tokens_batches": 9e-06, + "output_cost_per_token_above_200k_tokens_flex": 9e-06 }, "gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, + "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 5e-08, - "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 9e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_above_200k_tokens": 1e-06, + "input_cost_per_audio_token_above_200k_tokens_batches": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_flex": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_priority": 1.8e-06, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_audio_token_flex": 5e-07, + "input_cost_per_audio_token_priority": 1.8e-06, "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.4e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -30857,7 +33214,9 @@ "text" ], "supports_audio_output": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -30868,36 +33227,19 @@ "supports_url_context": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 9e-07, - "input_cost_per_audio_token_priority": 1.8e-06, - "output_cost_per_token_priority": 5.4e-06, - "cache_read_input_token_cost_priority": 9e-08, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 5e-07, - "input_cost_per_token_batches": 2.5e-07, - "input_cost_per_token_flex": 2.5e-07, - "output_cost_per_token_batches": 1.5e-06, - "output_cost_per_token_flex": 1.5e-06 + "web_search_billing_unit": "per_query" }, "gemini-omni-flash-preview": { "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 131072, + "max_output_tokens": 57920, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-flash-preview", "supported_endpoints": [ "/v1/chat/completions" ], @@ -30915,23 +33257,35 @@ "supports_reasoning": true, "supports_system_messages": true, "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "deprecation_date": "2026-11-06" }, "gemini-3.5-flash": { - "prompt_cache_min_tokens": 4096, - "deprecation_date": "2027-05-19", "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, + "cache_read_input_token_cost_flex": 7.5e-08, + "cache_read_input_token_cost_priority": 2.7e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1.5e-06, + "input_cost_per_audio_token_priority": 2.7e-06, "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_flex": 7.5e-07, + "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, + "output_cost_per_token_batches": 4.5e-06, + "output_cost_per_token_flex": 4.5e-06, + "output_cost_per_token_priority": 1.62e-05, + "prompt_cache_min_tokens": 4096.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -30946,9 +33300,11 @@ "supported_output_modalities": [ "text" ], - "supports_audio_output": false, "supports_audio_input": true, + "supports_audio_output": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -30960,23 +33316,7 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 2.7e-06, - "input_cost_per_audio_token_priority": 2.7e-06, - "output_cost_per_token_priority": 1.62e-05, - "cache_read_input_token_cost_priority": 2.7e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_token_batches": 7.5e-07, - "output_cost_per_token_batches": 4.5e-06, - "input_cost_per_token_flex": 7.5e-07, - "output_cost_per_token_flex": 4.5e-06, - "cache_read_input_token_cost_flex": 7.5e-08 + "web_search_billing_unit": "per_query" }, "gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, @@ -30989,7 +33329,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -31012,12 +33351,14 @@ ], "supports_audio_output": false, "supports_audio_input": true, + "supports_computer_use": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -31029,11 +33370,14 @@ "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, "deprecation_date": "2026-11-19", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "gemini-3.8-flash", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -31048,7 +33392,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -31071,6 +33414,7 @@ ], "supports_audio_output": false, "supports_audio_input": true, + "supports_computer_use": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -31078,6 +33422,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -31089,31 +33434,39 @@ "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, "deprecation_date": "2027-01-28", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "gemini-3.8-flash", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "gemini-3.8-flash": { - "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -31129,32 +33482,25 @@ "supported_output_modalities": [ "text" ], - "supports_audio_output": false, "supports_audio_input": true, + "supports_audio_output": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 1.35e-06, - "output_cost_per_token_priority": 6.75e-06, - "cache_read_input_token_cost_priority": 1.35e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "web_search_billing_unit": "per_query" }, "gemini-3.8-flash-cyber": { "cache_read_input_token_cost": 1.5e-07, @@ -31168,7 +33514,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 7.5e-06, "output_cost_per_token": 7.5e-06, @@ -31197,6 +33542,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_url_context": false, @@ -31208,13 +33554,14 @@ "gemini/gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-flash-tts", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, @@ -31249,7 +33596,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "metadata": { "notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true @@ -31272,7 +33618,6 @@ "litellm_provider": "gemini", "max_input_tokens": 2097152, "max_output_tokens": 8192, - "max_tokens": 8192, "metadata": { "notes": "Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true @@ -31293,7 +33638,7 @@ "input_cost_per_token": 3.5e-07, "litellm_provider": "gemini", "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.05e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", @@ -31307,7 +33652,7 @@ "input_cost_per_token": 3.5e-07, "litellm_provider": "gemini", "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.05e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", @@ -31331,7 +33676,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, @@ -31351,7 +33695,6 @@ "litellm_provider": "gemini", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, @@ -31367,7 +33710,6 @@ "litellm_provider": "gemini", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, @@ -31403,7 +33745,6 @@ "litellm_provider": "gemini", "max_input_tokens": 32767, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, @@ -31422,7 +33763,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_image": 0.04, "output_cost_per_token": 0, @@ -31447,10 +33787,9 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], @@ -31465,18 +33804,20 @@ "supports_system_messages": false, "supports_vision": false, "supports_web_search": false, - "output_cost_per_image": 0.08 + "output_cost_per_image": 0.08, + "successor_model": "gemini/lyria-3.5" }, "gemini/veo-3.1-fast-generate-preview": { "deprecation_date": "2026-10-22", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, "output_cost_per_second_4k": 0.3, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], @@ -31486,13 +33827,14 @@ }, "gemini/veo-3.1-generate-preview": { "deprecation_date": "2026-10-22", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], @@ -31502,13 +33844,14 @@ }, "gemini/veo-3.1-lite-generate-preview": { "deprecation_date": "2026-10-22", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.08, - "source": "https://ai.google.dev/gemini-api/docs/video", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], @@ -31519,7 +33862,6 @@ "gemini/veo-3.1-fast-generate-001": { "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -31535,7 +33877,6 @@ "gemini/veo-3.1-generate-001": { "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, @@ -31548,11 +33889,15 @@ ] }, "github_copilot/claude-fable-5": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" @@ -31566,11 +33911,15 @@ "thinking_always_on": true }, "github_copilot/claude-fable-5.1": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-05, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" @@ -31583,6 +33932,9 @@ "supports_vision": true, "thinking_always_on": true }, + "github_copilot/claude-fable-latest": { + "alias_of": "github_copilot/claude-fable-5.2" + }, "github_copilot/claude-haiku-4.5": { "cache_creation_input_token_cost": 1.25e-06, "cache_read_input_token_cost": 1e-07, @@ -31590,7 +33942,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 5e-06, "supported_endpoints": [ @@ -31611,7 +33962,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_above_100k_tokens": 2.5e-06, @@ -31628,12 +33978,20 @@ "supports_vision": true, "thinking_always_on": false }, + "github_copilot/claude-haiku-latest": { + "alias_of": "github_copilot/claude-haiku-5.5" + }, "github_copilot/claude-opus-4.8": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "deprecation_date": "2026-11-16", + "input_cost_per_token": 5e-06, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" @@ -31646,11 +34004,16 @@ "supports_vision": true }, "github_copilot/claude-opus-4.8-fast": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_read_input_token_cost": 1e-06, + "deprecation_date": "2026-11-16", + "input_cost_per_token": 1e-05, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" @@ -31663,11 +34026,16 @@ "supports_vision": true }, "github_copilot/claude-opus-5": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "deprecation_date": "2026-11-16", + "input_cost_per_token": 5e-06, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" @@ -31680,11 +34048,15 @@ "supports_vision": true }, "github_copilot/claude-opus-5.5": { + "cache_creation_input_token_cost": 5e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" @@ -31697,12 +34069,19 @@ "supports_vision": true, "thinking_always_on": true }, + "github_copilot/claude-opus-latest": { + "alias_of": "github_copilot/claude-opus-5.5" + }, "github_copilot/claude-sonnet-5": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" @@ -31715,11 +34094,15 @@ "supports_vision": true }, "github_copilot/claude-sonnet-5.5": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" @@ -31732,39 +34115,50 @@ "supports_vision": true, "thinking_always_on": true }, + "github_copilot/claude-sonnet-latest": { + "alias_of": "github_copilot/claude-sonnet-5.5" + }, "github_copilot/gemini-3.7-flash": { + "cache_read_input_token_cost": 7.5e-08, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 7.5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_vision": true }, "github_copilot/gemini-3.8-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_vision": true }, "github_copilot/gpt-3.5-turbo": { "litellm_provider": "github_copilot", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -31772,7 +34166,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -31780,7 +34173,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -31788,7 +34180,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -31796,28 +34187,31 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true }, "github_copilot/gpt-4.1": { + "deprecation_date": "2026-06-01", + "deprecation_source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-4.1-2025-04-14": { + "deprecation_date": "2026-06-01", + "deprecation_source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -31831,7 +34225,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -31841,7 +34234,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -31851,7 +34243,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true @@ -31860,7 +34251,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -31870,7 +34260,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true @@ -31879,20 +34268,20 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true }, "github_copilot/gpt-5-mini": { "cache_read_input_token_cost": 2.5e-08, + "deprecation_date": "2026-10-19", "input_cost_per_token": 2.5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://github.blog/changelog/2026-10-19-github-copilot-models-deprecated-on-october-19-2026", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -31904,7 +34293,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "supported_endpoints": [ @@ -31917,11 +34305,19 @@ "supports_vision": true }, "github_copilot/gpt-5.4": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "deprecation_date": "2026-10-19", + "deprecation_source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 5e-06, "litellm_provider": "github_copilot", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -31933,11 +34329,15 @@ "supports_vision": true }, "github_copilot/gpt-5.4-mini": { + "cache_read_input_token_cost": 7.5e-08, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 7.5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 4.5e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], @@ -31948,11 +34348,19 @@ "supports_vision": true }, "github_copilot/gpt-5.5": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "deprecation_date": "2026-10-19", + "deprecation_source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, "litellm_provider": "github_copilot", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], @@ -31963,11 +34371,19 @@ "supports_vision": true }, "github_copilot/gpt-5.6-luna": { + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_200k_tokens": 5e-07, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_200k_tokens": 4e-08, + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_200k_tokens": 4e-07, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_200k_tokens": 1.8e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], @@ -31978,11 +34394,19 @@ "supports_vision": true }, "github_copilot/gpt-5.6-sol": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, "litellm_provider": "github_copilot", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], @@ -31993,11 +34417,20 @@ "supports_vision": true }, "github_copilot/gpt-5.6-terra": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "deprecation_date": "2026-11-16", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, "litellm_provider": "github_copilot", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], @@ -32008,11 +34441,19 @@ "supports_vision": true }, "github_copilot/gpt-6-astra": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, "litellm_provider": "github_copilot", - "max_input_tokens": 272000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 5e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], @@ -32022,12 +34463,23 @@ "supports_response_schema": true, "supports_vision": true }, + "github_copilot/gpt-astra-latest": { + "alias_of": "github_copilot/gpt-6-astra" + }, "github_copilot/gpt-6-luna": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, "litellm_provider": "github_copilot", - "max_input_tokens": 272000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], @@ -32037,12 +34489,23 @@ "supports_response_schema": true, "supports_vision": true }, + "github_copilot/gpt-luna-latest": { + "alias_of": "github_copilot/gpt-6-luna" + }, "github_copilot/gpt-6-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, "litellm_provider": "github_copilot", - "max_input_tokens": 272000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], @@ -32053,11 +34516,19 @@ "supports_vision": true }, "github_copilot/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, "litellm_provider": "github_copilot", - "max_input_tokens": 272000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], @@ -32067,12 +34538,18 @@ "supports_response_schema": true, "supports_vision": true }, + "github_copilot/gpt-sol-latest": { + "alias_of": "github_copilot/gpt-6.1-sol" + }, "github_copilot/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, "litellm_provider": "github_copilot", "max_input_tokens": 917504, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], @@ -32081,12 +34558,18 @@ "supports_response_schema": true, "supports_vision": true }, + "github_copilot/kimi-latest": { + "alias_of": "github_copilot/kimi-k3" + }, "github_copilot/mai-code-1.1-flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 1.2e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], @@ -32098,19 +34581,16 @@ "github_copilot/text-embedding-3-small": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding" }, "github_copilot/text-embedding-3-small-inference": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding" }, "github_copilot/text-embedding-ada-002": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding" }, "chatgpt/gpt-6-sol": { @@ -32122,7 +34602,6 @@ ], "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_max_reasoning_effort": true, @@ -32143,7 +34622,6 @@ ], "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_max_reasoning_effort": true, @@ -32164,7 +34642,6 @@ ], "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_max_reasoning_effort": true, @@ -32185,7 +34662,6 @@ ], "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_max_reasoning_effort": true, @@ -32202,7 +34678,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.5", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -32222,7 +34697,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.6-luna", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -32242,7 +34716,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.6-sol", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -32262,7 +34735,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.6-terra", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -32281,7 +34753,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -32301,7 +34772,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -32319,7 +34789,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -32329,15 +34798,14 @@ "supports_response_schema": true, "supports_vision": true, "supports_reasoning": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.3-codex-spark": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -32351,7 +34819,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -32366,7 +34833,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -32382,7 +34848,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -32397,7 +34862,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -32417,7 +34881,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -32432,7 +34895,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -32448,7 +34910,6 @@ "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, @@ -32459,7 +34920,6 @@ "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, @@ -32471,7 +34931,6 @@ "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, @@ -32482,7 +34941,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -32491,7 +34949,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -32500,7 +34957,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 4096, - "max_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560 @@ -32509,7 +34965,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 4096, - "max_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2048 @@ -32519,7 +34974,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_function_calling": true, @@ -32531,7 +34985,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -32542,7 +34995,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -32553,7 +35005,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -32564,7 +35015,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.4e-05, "supports_function_calling": true @@ -32574,7 +35024,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true @@ -32584,7 +35033,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true @@ -32594,7 +35042,6 @@ "litellm_provider": "gmi", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -32605,7 +35052,6 @@ "litellm_provider": "gmi", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -32616,7 +35062,6 @@ "litellm_provider": "gmi", "max_input_tokens": 163840, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true @@ -32626,7 +35071,6 @@ "litellm_provider": "gmi", "max_input_tokens": 163840, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 8.8e-07, "supports_function_calling": true @@ -32636,7 +35080,6 @@ "litellm_provider": "gmi", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, @@ -32648,7 +35091,6 @@ "litellm_provider": "gmi", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, @@ -32657,35 +35099,37 @@ "litellm_provider": "gmi", "max_input_tokens": 196608, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, "baseten/MiniMaxAI/MiniMax-M2.5": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 3e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 1.2e-06 }, "baseten/nvidia/Nemotron-120B-A12B": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 3e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 7.5e-07 }, "baseten/zai-org/GLM-5": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 9.5e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 3.15e-06 }, "baseten/zai-org/GLM-4.7": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "max_input_tokens": 200000, "max_output_tokens": 200000, - "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://inference.baseten.co/v1/models", @@ -32697,24 +35141,28 @@ "supports_vision": false }, "baseten/zai-org/GLM-4.6": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 2.2e-06 }, "baseten/moonshotai/Kimi-K2.5": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 3e-06 }, "baseten/moonshotai/Kimi-K2-Thinking": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 2.5e-06 }, "baseten/moonshotai/Kimi-K2-Instruct-0905": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", @@ -32726,7 +35174,6 @@ "litellm_provider": "baseten", "max_input_tokens": 128072, "max_output_tokens": 128072, - "max_tokens": 128072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inference.baseten.co/v1/models", @@ -32738,12 +35185,14 @@ "supports_vision": false }, "baseten/deepseek-ai/DeepSeek-V3.1": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 5e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 1.5e-06 }, "baseten/deepseek-ai/DeepSeek-V3-0324": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 7.7e-07, "litellm_provider": "baseten", "mode": "chat", @@ -32754,7 +35203,6 @@ "litellm_provider": "gmi", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-06, "supports_vision": true @@ -32764,22 +35212,25 @@ "litellm_provider": "gmi", "max_input_tokens": 202752, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2e-06 }, "google.gemma-3-12b-it": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 9e-08, + "input_cost_per_token_batches": 5e-08, "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.9e-07, + "output_cost_per_token_batches": 1.5e-07, "output_cost_per_token_flex": 1.5e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-google-gemma-3-12b-it.html", + "output_cost_per_token_priority": 5.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, @@ -32788,16 +35239,20 @@ }, "google.gemma-3-27b-it": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.3e-07, + "input_cost_per_token_batches": 1.2e-07, "input_cost_per_token_flex": 1.2e-07, + "input_cost_per_token_priority": 4e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 3.8e-07, + "output_cost_per_token_batches": 1.9e-07, "output_cost_per_token_flex": 1.9e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-google-gemma-3-27b-pt.html", + "output_cost_per_token_priority": 6.7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, @@ -32806,16 +35261,20 @@ }, "google.gemma-3-4b-it": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 4e-08, + "input_cost_per_token_batches": 2e-08, "input_cost_per_token_flex": 2e-08, + "input_cost_per_token_priority": 7e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8e-08, + "output_cost_per_token_batches": 4e-08, "output_cost_per_token_flex": 4e-08, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-google-gemma-3-4b-it.html", + "output_cost_per_token_priority": 1.4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -32837,11 +35296,12 @@ "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "deprecation_date": "2027-04-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "global.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -32863,21 +35323,26 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, "output_cost_per_token_batches": 7.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "global.anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -32896,7 +35361,11 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.25e-06, @@ -32907,7 +35376,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -32924,17 +35392,26 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-07, - "output_cost_per_token_batches": 2.5e-06 + "output_cost_per_token_batches": 2.5e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "global.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_priority": 1.3125e-07, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -32946,13 +35423,15 @@ }, "gpt-3.5-turbo": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 5e-07, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_prompt_caching": true, @@ -32961,14 +35440,16 @@ }, "gpt-3.5-turbo-0125": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 7.5e-07, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -32979,14 +35460,16 @@ }, "gpt-3.5-turbo-1106": { "deprecation_date": "2026-09-28", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -32997,24 +35480,26 @@ }, "gpt-3.5-turbo-16k": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-06, + "fedramp_uplift_multiplier": 1.1, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-3.5-turbo-instruct": { "deprecation_date": "2026-09-28", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1.5e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06, "source": "https://developers.openai.com/api/docs/pricing" @@ -33024,19 +35509,20 @@ "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, "max_output_tokens": 4097, - "max_tokens": 4097, "mode": "completion", "output_cost_per_token": 2e-06 }, "gpt-4": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 3e-05, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, + "fedramp_uplift_multiplier": 1.1, "supports_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, @@ -33044,14 +35530,16 @@ }, "gpt-4-0613": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 3e-05, "input_cost_per_token_batches": 1.5e-05, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -33061,13 +35549,15 @@ }, "gpt-4-1106-preview": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, + "fedramp_uplift_multiplier": 1.1, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -33076,13 +35566,15 @@ }, "gpt-4-turbo": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, + "fedramp_uplift_multiplier": 1.1, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -33093,14 +35585,16 @@ }, "gpt-4-turbo-2024-04-09": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1e-05, "input_cost_per_token_batches": 5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1.5e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -33114,15 +35608,18 @@ "gpt-4.1": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, "search_context_cost_per_query": { @@ -33157,15 +35654,18 @@ "gpt-4.1-2025-04-14": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 2e-06, "input_cost_per_token_priority": 3.5e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 1.4e-05, "output_cost_per_token_batches": 4e-06, "search_context_cost_per_query": { @@ -33200,15 +35700,18 @@ "gpt-4.1-mini": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, "input_cost_per_token_priority": 7e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, "search_context_cost_per_query": { @@ -33243,15 +35746,18 @@ "gpt-4.1-mini-2025-04-14": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 4e-07, "input_cost_per_token_priority": 7e-07, "input_cost_per_token_batches": 2e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2.8e-06, "output_cost_per_token_batches": 8e-07, "search_context_cost_per_query": { @@ -33287,15 +35793,17 @@ "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 5e-08, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-luna", "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_priority": 2e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2e-07, "output_cost_per_token_priority": 8e-07, "source": "https://developers.openai.com/api/docs/pricing", @@ -33325,15 +35833,17 @@ "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 5e-08, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-luna", "input_cost_per_token": 1e-07, "input_cost_per_token_priority": 2e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 8e-07, "output_cost_per_token_batches": 2e-07, "source": "https://developers.openai.com/api/docs/pricing", @@ -33362,15 +35872,18 @@ "gpt-4o": { "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_priority": 2.125e-06, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "input_cost_per_token_priority": 4.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 1.7e-05, "source": "https://developers.openai.com/api/docs/pricing", @@ -33385,15 +35898,17 @@ }, "gpt-4o-2024-05-13": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_priority": 8.75e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_priority": 2.625e-05, "source": "https://developers.openai.com/api/docs/pricing", @@ -33408,15 +35923,18 @@ "gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_priority": 2.125e-06, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 2.5e-06, "input_cost_per_token_priority": 4.25e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 1.7e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", @@ -33432,15 +35950,18 @@ "gpt-4o-2024-11-20": { "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_priority": 2.125e-06, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 2.5e-06, "input_cost_per_token_priority": 4.25e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 1.7e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", @@ -33455,12 +35976,13 @@ }, "gpt-4o-audio-preview-2024-12-17": { "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, @@ -33473,12 +35995,13 @@ }, "gpt-4o-audio-preview-2025-06-03": { "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, @@ -33491,12 +36014,13 @@ }, "gpt-audio": { "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -33533,7 +36057,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -33563,12 +36086,13 @@ }, "gpt-audio-2025-08-28": { "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -33601,12 +36125,13 @@ }, "gpt-audio-mini": { "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -33639,12 +36164,13 @@ }, "gpt-audio-mini-2025-10-06": { "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -33681,7 +36207,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -33711,20 +36236,25 @@ "supports_tool_choice": true, "supports_vision": false, "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-audio-1.5", "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.25e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_priority": 2.5e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-07, "output_cost_per_token_priority": 1e-06, "supports_function_calling": true, @@ -33745,15 +36275,18 @@ "gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.25e-07, + "deprecation_date": "2027-01-14", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 2.5e-07, "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 1e-06, "output_cost_per_token_batches": 3e-07, "search_context_cost_per_query": { @@ -33773,12 +36306,12 @@ }, "gpt-4o-mini-audio-preview-2024-12-17": { "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 1.5e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 6e-07, @@ -33793,12 +36326,12 @@ "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -33816,9 +36349,9 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-07, "search_context_cost_per_query": { "search_context_size_high": 0.025, @@ -33837,15 +36370,17 @@ }, "gpt-4o-mini-search-preview-2025-03-11": { "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-07, "search_context_cost_per_query": { "search_context_size_high": 0.025, @@ -33875,10 +36410,15 @@ "/v1/audio/transcriptions" ], "deprecation_date": "2027-02-26", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-live-transcribe", "input_cost_per_second": 5e-05, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini-tts": { + "deprecation_date": "2027-01-06", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", @@ -33899,6 +36439,8 @@ }, "gpt-4o-mini-tts-2025-03-20": { "deprecation_date": "2027-01-06", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", @@ -33924,9 +36466,9 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.025, @@ -33945,15 +36487,17 @@ }, "gpt-4o-search-preview-2025-03-11": { "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.025, @@ -33983,14 +36527,19 @@ "/v1/audio/transcriptions" ], "deprecation_date": "2027-02-26", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-live-transcribe", "input_cost_per_second": 0.0001, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-image-1.5": { "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.3e-07, "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", @@ -33999,6 +36548,7 @@ "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3.2e-05, + "output_cost_per_image_token_batches": 1.6e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ @@ -34012,6 +36562,8 @@ "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.3e-07, "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", @@ -34020,6 +36572,7 @@ "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3.2e-05, + "output_cost_per_image_token_batches": 1.6e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ @@ -34030,8 +36583,11 @@ }, "gpt-image-2": { "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.25e-07, + "deprecation_date": "2027-02-10", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", @@ -34039,7 +36595,9 @@ "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, "source": "https://developers.openai.com/api/docs/pricing", + "successor_model": "gpt-image-2.6-sunburst", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -34050,12 +36608,15 @@ "gpt-image-2-2026-04-21": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2027-02-10", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, "output_cost_per_image_token": 3e-05, "source": "https://developers.openai.com/api/docs/pricing", + "successor_model": "gpt-image-2.6-sunburst", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -34065,6 +36626,7 @@ }, "gpt-image-2.5-flare": { "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.25e-07, "input_cost_per_token": 5e-06, @@ -34074,6 +36636,7 @@ "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -34100,6 +36663,7 @@ }, "gpt-image-2.5-sunburst": { "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.25e-07, "input_cost_per_token": 5e-06, @@ -34109,6 +36673,7 @@ "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -34135,6 +36700,8 @@ }, "low/1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", @@ -34147,6 +36714,8 @@ }, "low/1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -34159,6 +36728,8 @@ }, "low/1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -34171,6 +36742,8 @@ }, "medium/1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.034, "litellm_provider": "openai", "mode": "image_generation", @@ -34183,6 +36756,8 @@ }, "medium/1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.05, "litellm_provider": "openai", "mode": "image_generation", @@ -34195,6 +36770,8 @@ }, "medium/1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.05, "litellm_provider": "openai", "mode": "image_generation", @@ -34207,6 +36784,8 @@ }, "high/1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.133, "litellm_provider": "openai", "mode": "image_generation", @@ -34219,6 +36798,8 @@ }, "high/1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.2, "litellm_provider": "openai", "mode": "image_generation", @@ -34231,6 +36812,8 @@ }, "high/1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.2, "litellm_provider": "openai", "mode": "image_generation", @@ -34243,6 +36826,8 @@ }, "standard/1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", @@ -34255,6 +36840,8 @@ }, "standard/1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -34267,6 +36854,8 @@ }, "standard/1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -34279,6 +36868,8 @@ }, "1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", @@ -34291,6 +36882,8 @@ }, "1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -34303,6 +36896,8 @@ }, "1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -34323,7 +36918,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "low/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -34335,7 +36932,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "low/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -34347,7 +36946,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "medium/1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.034, @@ -34359,7 +36960,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "medium/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.05, @@ -34371,7 +36974,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "medium/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.05, @@ -34383,7 +36988,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "high/1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.133, @@ -34395,7 +37002,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "high/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.2, @@ -34407,7 +37016,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "high/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.2, @@ -34419,7 +37030,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "standard/1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.009, @@ -34431,7 +37044,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "standard/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -34443,7 +37058,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "standard/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -34455,7 +37072,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.009, @@ -34467,7 +37086,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -34479,7 +37100,9 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -34491,13 +37114,18 @@ ], "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-12-01" + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst" }, "gpt-5": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, + "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, @@ -34505,12 +37133,19 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 2e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34547,13 +37182,15 @@ "gpt-5-codex": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5-codex", "supported_endpoints": [ "/v1/responses" @@ -34586,10 +37223,17 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34627,18 +37271,22 @@ "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": false, - "deprecation_date": "2027-04-01" + "deprecation_date": "2027-04-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-sol" }, "gpt-5.1-codex-mini": { "cache_read_input_token_cost": 2.5e-08, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 2.5e-07, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini", "supported_endpoints": [ "/v1/responses" @@ -34663,13 +37311,15 @@ "gpt-5.1-codex-max": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-max", "supported_endpoints": [ "/v1/responses" @@ -34695,13 +37345,15 @@ "gpt-5.1-codex": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex", "supported_endpoints": [ "/v1/responses" @@ -34727,13 +37379,15 @@ "gpt-5.1-chat-latest": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-chat-latest", "supported_endpoints": [ "/v1/chat/completions", @@ -34761,15 +37415,25 @@ "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, + "deprecation_date": "2027-04-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-sol", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34818,10 +37482,17 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2.8e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34849,6 +37520,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -34864,13 +37536,15 @@ "gpt-5.2-codex": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.75e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-codex", "supported_endpoints": [ "/v1/responses" @@ -34896,13 +37570,15 @@ "gpt-5.2-chat-latest": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-08-10", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.75e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-chat-latest", "supported_endpoints": [ "/v1/chat/completions", @@ -34935,10 +37611,17 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2.8e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34966,6 +37649,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -34984,10 +37668,17 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 8.4e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "pro" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35026,10 +37717,17 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 8.4e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "pro" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35064,6 +37762,16 @@ }, "gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_12hr": 2.5e-05, + "cache_creation_input_token_cost_above_12hr_ultrafast": 0.00015, + "cache_creation_input_token_cost_above_12hr_batches": 1.25e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 5e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2.5e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 2.5e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 0.0001, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 0.0003, + "cache_creation_input_token_cost_above_12hr_flex": 1.25e-05, + "cache_creation_input_token_cost_above_12hr_priority": 5e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-05, @@ -35096,7 +37804,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, @@ -35108,8 +37815,18 @@ "output_cost_per_token_flex": 2.5e-05, "output_cost_per_token_priority": 0.0001, "output_cost_per_token_ultrafast": 0.0003, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35142,12 +37859,24 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "gpt-astra-latest": { + "alias_of": "gpt-6-astra" + }, "gpt-6-sol": { "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_12hr": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_flex": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_priority": 1e-05, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, @@ -35174,7 +37903,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, @@ -35184,8 +37912,18 @@ "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 2e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35218,23 +37956,32 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_decisions": 1e-07, + "cache_creation_input_token_cost_above_12hr": 2.5e-07, + "cache_creation_input_token_cost_above_12hr_batches": 1.25e-07, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2.5e-07, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 2.5e-07, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 1e-06, + "cache_creation_input_token_cost_above_12hr_flex": 1.25e-07, + "cache_creation_input_token_cost_above_12hr_priority": 5e-07, + "cache_creation_input_token_cost_decisions": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, - "cache_creation_input_token_cost_above_272k_tokens_decisions": 2e-07, + "cache_creation_input_token_cost_above_272k_tokens_decisions": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-07, "cache_creation_input_token_cost_flex": 6.25e-08, "cache_creation_input_token_cost_priority": 2.5e-07, "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_decisions": 1e-07, + "cache_read_input_token_cost_decisions": 1e-08, "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "cache_read_input_token_cost_above_272k_tokens_decisions": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_decisions": 2e-08, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 4e-08, "cache_read_input_token_cost_batches": 5e-09, @@ -35256,7 +38003,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_decisions": 0.0, @@ -35268,8 +38014,18 @@ "output_cost_per_token_above_272k_tokens_batches": 3.75e-07, "output_cost_per_token_flex": 2.5e-07, "output_cost_per_token_priority": 1e-06, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35303,12 +38059,22 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "gpt-luna-latest": { + "alias_of": "gpt-6-luna" + }, "gpt-5.6": { "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_12hr": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 2e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 4e-05, + "cache_creation_input_token_cost_above_12hr_flex": 5e-06, + "cache_creation_input_token_cost_above_12hr_priority": 2e-05, "cache_creation_input_token_cost_above_272k_tokens": 1e-05, "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, @@ -35335,7 +38101,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -35345,8 +38110,18 @@ "output_cost_per_token_above_272k_tokens_batches": 1.5e-05, "output_cost_per_token_flex": 1e-05, "output_cost_per_token_priority": 4e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35376,12 +38151,21 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-5.6-sol": { "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_12hr": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 2e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 4e-05, + "cache_creation_input_token_cost_above_12hr_batches": 5e-06, + "cache_creation_input_token_cost_above_12hr_flex": 5e-06, + "cache_creation_input_token_cost_above_12hr_priority": 2e-05, "cache_creation_input_token_cost_above_272k_tokens": 1e-05, "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, @@ -35408,7 +38192,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -35418,8 +38201,18 @@ "output_cost_per_token_above_272k_tokens_batches": 1.5e-05, "output_cost_per_token_flex": 1e-05, "output_cost_per_token_priority": 4e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35451,12 +38244,21 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_12hr": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_flex": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_priority": 1e-05, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, @@ -35483,7 +38285,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, @@ -35493,8 +38294,18 @@ "output_cost_per_token_above_272k_tokens_batches": 9e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.4e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35525,12 +38336,21 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_12hr": 5e-07, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-07, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-07, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-06, + "cache_creation_input_token_cost_above_12hr_batches": 2.5e-07, + "cache_creation_input_token_cost_above_12hr_flex": 2.5e-07, + "cache_creation_input_token_cost_above_12hr_priority": 1e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, @@ -35557,7 +38377,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, @@ -35567,8 +38386,18 @@ "output_cost_per_token_above_272k_tokens_batches": 9e-07, "output_cost_per_token_flex": 6e-07, "output_cost_per_token_priority": 2.4e-06, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35599,23 +38428,25 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-5.6-cyber": { "cache_creation_input_token_cost": 1.5625e-05, + "cache_creation_input_token_cost_above_12hr": 3.125e-05, "cache_creation_input_token_cost_above_272k_tokens": 3.125e-05, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens": 2.5e-06, "input_cost_per_token": 1.25e-05, "input_cost_per_token_above_272k_tokens": 2.5e-05, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ "/v1/chat/completions", @@ -35650,11 +38481,11 @@ "input_cost_per_token": 1.25e-05, "input_cost_per_token_above_272k_tokens": 2.5e-05, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ "/v1/chat/completions", @@ -35689,11 +38520,11 @@ "input_cost_per_token": 1.25e-05, "input_cost_per_token_above_272k_tokens": 2.5e-05, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 7.5e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ "/v1/responses" @@ -35729,9 +38560,9 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 3e-05, "supported_endpoints": [ "/v1/chat/completions", @@ -35768,9 +38599,9 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 3e-05, "supported_endpoints": [ "/v1/responses" @@ -35802,12 +38633,20 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, + "fedramp_uplift_multiplier": 1.1, "reasoning_effort_levels": [ "medium" ], + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -35848,7 +38687,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, @@ -35856,8 +38694,17 @@ "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_above_272k_tokens_batches": 2.25e-05, "output_cost_per_token_priority": 7.5e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35884,6 +38731,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -35910,7 +38758,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, @@ -35918,8 +38765,17 @@ "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_above_272k_tokens_batches": 2.25e-05, "output_cost_per_token_priority": 7.5e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -35946,6 +38802,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -35965,15 +38822,23 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, "output_cost_per_token_above_272k_tokens_batches": 0.000135, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36000,6 +38865,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -36016,15 +38882,23 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, "output_cost_per_token_above_272k_tokens_batches": 0.000135, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36051,6 +38925,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -36074,7 +38949,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, @@ -36082,8 +38956,17 @@ "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_above_272k_tokens_batches": 1.125e-05, "output_cost_per_token_priority": 3e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -36105,6 +38988,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", @@ -36131,7 +39015,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, @@ -36139,8 +39022,17 @@ "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_above_272k_tokens_batches": 1.125e-05, "output_cost_per_token_priority": 3e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -36162,6 +39054,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", @@ -36181,15 +39074,23 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, "output_cost_per_token_above_272k_tokens_batches": 0.000135, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36215,6 +39116,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -36233,15 +39135,23 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, "output_cost_per_token_above_272k_tokens_batches": 0.000135, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36267,6 +39177,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -36288,14 +39199,22 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_priority": 9e-06, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36322,6 +39241,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -36330,6 +39250,9 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "gpt-mini-latest": { + "alias_of": "gpt-5.4-mini" + }, "gpt-5.4-mini-2026-03-17": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, @@ -36342,14 +39265,22 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_priority": 9e-06, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36376,6 +39307,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -36394,13 +39326,21 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 6.25e-07, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36434,25 +39374,38 @@ "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "deprecation_date": "2027-04-01" + "deprecation_date": "2027-04-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna" }, "gpt-5.4-nano-2026-03-17": { "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_flex": 1e-08, + "deprecation_date": "2027-04-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-luna", "input_cost_per_token": 2e-07, "input_cost_per_token_flex": 1e-07, "input_cost_per_token_batches": 1e-07, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 6.25e-07, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36488,15 +39441,25 @@ "supports_minimal_reasoning_effort": false }, "gpt-5-pro": { + "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 272000, - "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 6e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "pro" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36531,15 +39494,24 @@ }, "gpt-5-pro-2025-10-06": { "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 272000, - "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 6e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "pro" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36578,6 +39550,8 @@ "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, @@ -36585,12 +39559,19 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 2e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36627,13 +39608,15 @@ "gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.2-chat-latest", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -36663,13 +39646,15 @@ "gpt-5-chat-latest": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5-chat-latest", "supported_endpoints": [ "/v1/chat/completions", @@ -36700,10 +39685,17 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2.8e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36729,23 +39721,28 @@ "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true, - "deprecation_date": "2027-04-01" + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "deprecation_date": "2027-04-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-6-sol" }, "gpt-5.3-chat-latest": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-08-10", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.75e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.3-chat-latest", "supported_endpoints": [ "/v1/chat/completions", @@ -36773,6 +39770,9 @@ "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, @@ -36780,12 +39780,19 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_flex": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36825,6 +39832,8 @@ "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, @@ -36832,12 +39841,19 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_flex": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36875,18 +39891,27 @@ "cache_read_input_token_cost": 5e-09, "cache_read_input_token_cost_batches": 2.5e-09, "cache_read_input_token_cost_flex": 2.5e-09, + "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-luna", "input_cost_per_token": 5e-08, "input_cost_per_token_batches": 2.5e-08, "input_cost_per_token_flex": 2.5e-08, - "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2e-07, "output_cost_per_token_flex": 2e-07, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36925,18 +39950,26 @@ "cache_read_input_token_cost_batches": 2.5e-09, "cache_read_input_token_cost_flex": 2.5e-09, "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-luna", "input_cost_per_token": 5e-08, "input_cost_per_token_batches": 2.5e-08, - "input_cost_per_token_priority": 2.5e-06, "input_cost_per_token_flex": 2.5e-08, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2e-07, "output_cost_per_token_flex": 2e-07, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36975,6 +40008,8 @@ "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.3e-07, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image_token": 1e-05, "input_cost_per_image_token_batches": 5e-06, "input_cost_per_token": 5e-06, @@ -36990,9 +40025,12 @@ }, "gpt-image-1-mini": { "cache_read_input_image_token_cost": 2.5e-07, + "cache_read_input_image_token_cost_batches": 1.3e-07, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image_token": 2.5e-06, "input_cost_per_image_token_batches": 1.25e-06, "input_cost_per_token": 2e-06, @@ -37000,6 +40038,7 @@ "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_image_token": 8e-06, + "output_cost_per_image_token_batches": 4e-06, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations", @@ -37012,13 +40051,14 @@ "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -37053,7 +40093,6 @@ "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -37088,8 +40127,10 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "realtime", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, "source": "https://developers.openai.com/api/docs/pricing", @@ -37123,7 +40164,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, @@ -37146,6 +40186,8 @@ "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, @@ -37160,7 +40202,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -37183,6 +40224,8 @@ "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, @@ -37192,13 +40235,14 @@ "cache_read_input_image_token_cost": 8e-08, "cache_read_input_token_cost": 6e-08, "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -37228,13 +40272,14 @@ "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -37260,7 +40305,6 @@ }, "gradient_ai/alibaba-qwen3-32b": { "litellm_provider": "gradient_ai", - "max_tokens": 40960, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" @@ -37275,7 +40319,6 @@ "gradient_ai/anthropic-claude-3-opus": { "input_cost_per_token": 1.5e-05, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 7.5e-05, "supported_endpoints": [ @@ -37291,7 +40334,6 @@ "gradient_ai/anthropic-claude-3.5-haiku": { "input_cost_per_token": 8e-07, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 4e-06, "supported_endpoints": [ @@ -37307,7 +40349,6 @@ "gradient_ai/anthropic-claude-3.5-sonnet": { "input_cost_per_token": 3e-06, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.5e-05, "supported_endpoints": [ @@ -37323,7 +40364,6 @@ "gradient_ai/anthropic-claude-3.7-sonnet": { "input_cost_per_token": 3e-06, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.5e-05, "supported_endpoints": [ @@ -37339,7 +40379,6 @@ "gradient_ai/deepseek-r1-distill-llama-70b": { "input_cost_per_token": 9.9e-07, "litellm_provider": "gradient_ai", - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 9.9e-07, "supported_endpoints": [ @@ -37355,7 +40394,6 @@ "gradient_ai/llama3-8b-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "gradient_ai", - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 2e-07, "supported_endpoints": [ @@ -37371,7 +40409,6 @@ "gradient_ai/llama3.3-70b-instruct": { "input_cost_per_token": 6.5e-07, "litellm_provider": "gradient_ai", - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 6.5e-07, "supported_endpoints": [ @@ -37387,7 +40424,6 @@ "gradient_ai/mistral-nemo-instruct-2407": { "input_cost_per_token": 3e-07, "litellm_provider": "gradient_ai", - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 3e-07, "supported_endpoints": [ @@ -37402,7 +40438,6 @@ }, "gradient_ai/openai-gpt-4o": { "litellm_provider": "gradient_ai", - "max_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" @@ -37416,7 +40451,6 @@ }, "gradient_ai/openai-gpt-4o-mini": { "litellm_provider": "gradient_ai", - "max_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" @@ -37431,7 +40465,6 @@ "gradient_ai/openai-o3": { "input_cost_per_token": 2e-06, "litellm_provider": "gradient_ai", - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "supported_endpoints": [ @@ -37447,7 +40480,6 @@ "gradient_ai/openai-o3-mini": { "input_cost_per_token": 1.1e-06, "litellm_provider": "gradient_ai", - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supported_endpoints": [ @@ -37463,7 +40495,6 @@ "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", @@ -37475,7 +40506,6 @@ "lemonade/gpt-oss-20b-mxfp4-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", @@ -37487,7 +40517,6 @@ "lemonade/gpt-oss-120b-mxfp-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", @@ -37499,7 +40528,6 @@ "lemonade/Gemma-3-4b-it-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", @@ -37511,7 +40539,6 @@ "lemonade/Qwen3-4B-Instruct-2507-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", @@ -37525,7 +40552,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, "supports_function_calling": true, @@ -37537,7 +40563,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, "supports_function_calling": true, @@ -37551,7 +40576,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 1000000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.25e-05, "supports_function_calling": true, @@ -37565,7 +40589,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, "supports_function_calling": true, @@ -37574,22 +40597,11 @@ "supports_response_schema": true, "supports_vision": true }, - "groq/llama-guard-3-8b": { - "deprecation_date": "2025-06-06", - "input_cost_per_token": 2e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://console.groq.com/docs/model/llama-guard-3-8b" - }, "groq/meta-llama/llama-prompt-guard-2-22m": { "input_cost_per_token": 3e-08, "litellm_provider": "groq", "max_input_tokens": 512, "max_output_tokens": 512, - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://console.groq.com/docs/models" @@ -37599,7 +40611,6 @@ "litellm_provider": "groq", "max_input_tokens": 512, "max_output_tokens": 512, - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 4e-08, "source": "https://console.groq.com/docs/model/meta-llama/llama-prompt-guard-2-86m" @@ -37610,7 +40621,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-07, "search_context_cost_per_query": { @@ -37620,6 +40630,7 @@ }, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -37631,7 +40642,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, "search_context_cost_per_query": { @@ -37641,6 +40651,7 @@ }, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -37652,7 +40663,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, "search_context_cost_per_query": { @@ -37661,6 +40671,7 @@ "search_context_size_medium": 0.005 }, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -37671,7 +40682,6 @@ "litellm_provider": "groq", "max_input_tokens": 4000, "max_output_tokens": 50000, - "max_tokens": 50000, "mode": "audio_speech", "source": "https://console.groq.com/docs/model/canopylabs/orpheus-v1-english" }, @@ -37680,7 +40690,6 @@ "litellm_provider": "groq", "max_input_tokens": 4000, "max_output_tokens": 50000, - "max_tokens": 50000, "mode": "audio_speech", "source": "https://console.groq.com/docs/models" }, @@ -37698,7 +40707,6 @@ }, "heroku/claude-3-5-haiku": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -37708,7 +40716,6 @@ }, "heroku/claude-3-5-sonnet-latest": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -37718,7 +40725,6 @@ }, "heroku/claude-3-7-sonnet": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -37728,7 +40734,6 @@ }, "heroku/claude-4-sonnet": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -37738,6 +40743,8 @@ }, "high/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.167, "input_cost_per_pixel": 1.59263611e-07, "litellm_provider": "openai", @@ -37749,6 +40756,8 @@ }, "high/1024-x-1536/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.25, "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "openai", @@ -37760,6 +40769,8 @@ }, "high/1536-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.25, "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "openai", @@ -37769,12 +40780,62 @@ "/v1/images/generations" ] }, + "hostinger_router/gpt-5.2": { + "cache_read_input_token_cost": 0.00000021, + "input_cost_per_token": 0.0000021, + "litellm_provider": "hostinger_router", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000168, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "source": "https://router.hostinger.com/v1/models" + }, + "hostinger_router/claude-sonnet-5": { + "cache_creation_input_token_cost": 3.3e-06, + "cache_creation_input_token_cost_above_1hr": 5.28e-06, + "cache_read_input_token_cost": 2.64e-07, + "input_cost_per_token": 2.64e-06, + "litellm_provider": "hostinger_router", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.32e-05, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_response_schema": true, + "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], + "source": "https://router.hostinger.com/v1/models" + }, + "hostinger_router/text-embedding-3-large": { + "input_cost_per_token": 1.716e-07, + "litellm_provider": "hostinger_router", + "max_input_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://router.hostinger.com/v1/models" + }, + "hostinger_router/text-embedding-3-small": { + "input_cost_per_token": 3e-08, + "litellm_provider": "hostinger_router", + "max_input_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://router.hostinger.com/v1/models" + }, "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B": { "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -37787,7 +40848,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, @@ -37800,7 +40860,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -37813,7 +40872,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -37826,7 +40884,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "supports_function_calling": true, @@ -37839,7 +40896,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true, @@ -37852,7 +40908,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_function_calling": true, @@ -37865,7 +40920,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, @@ -37878,7 +40932,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true, @@ -37891,7 +40944,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -37904,7 +40956,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -37917,7 +40968,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -37930,7 +40980,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -37943,7 +40992,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -37956,7 +41004,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -37969,7 +41016,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "supports_function_calling": true, @@ -37982,7 +41028,6 @@ "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 3e-06 }, @@ -37991,7 +41036,6 @@ "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 1e-05 }, @@ -38000,7 +41044,6 @@ "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 1.5e-05 }, @@ -38009,7 +41052,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -38019,7 +41061,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -38029,7 +41070,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -38039,7 +41079,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -38049,7 +41088,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -38059,7 +41097,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -38069,7 +41106,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -38079,7 +41115,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -38089,17 +41124,31 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true }, + "jina-reranker-v3.5": { + "input_cost_per_token": 5e-08, + "litellm_provider": "jina_ai", + "max_input_tokens": 131072, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://api.jina.ai/v1/models" + }, + "jina-reranker-m0": { + "input_cost_per_token": 5e-08, + "litellm_provider": "jina_ai", + "max_input_tokens": 10240, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://api.jina.ai/v1/models" + }, "jina-reranker-v2-base-multilingual": { "input_cost_per_token": 5e-08, "litellm_provider": "jina_ai", "max_input_tokens": 1024, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://api.jina.ai/v1/models" @@ -38115,11 +41164,12 @@ "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "deprecation_date": "2027-04-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "jp.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -38141,7 +41191,11 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -38152,7 +41206,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -38169,14 +41222,17 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "crusoe/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 3e-06, "litellm_provider": "crusoe", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 7e-06, "supports_function_calling": false, @@ -38189,7 +41245,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -38202,7 +41257,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -38216,7 +41270,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, @@ -38229,7 +41282,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-06, "supports_function_calling": false, @@ -38242,7 +41294,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, @@ -38255,7 +41306,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, @@ -38269,7 +41319,6 @@ "litellm_provider": "inception", "max_input_tokens": 128000, "max_output_tokens": 50000, - "max_tokens": 50000, "mode": "chat", "output_cost_per_token": 7.5e-07, "supports_function_calling": true, @@ -38284,7 +41333,6 @@ "litellm_provider": "inception", "max_input_tokens": 260000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-07, "source": "https://docs.inceptionlabs.ai/get-started/models", @@ -38294,501 +41342,1234 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "text-completion-inception/mercury-edit-2": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "text-completion-inception", - "max_input_tokens": 32000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "completion", - "output_cost_per_token": 7.5e-07 - }, - "lambda_ai/deepseek-llama3.3-70b": { - "input_cost_per_token": 2e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-ai/DeepSeek-V3": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/deepseek-r1-0528": { - "input_cost_per_token": 2e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-ai/DeepSeek-V4-Flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/deepseek-r1-671b": { - "input_cost_per_token": 8e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-ai/DeepSeek-V4-Flash-0731": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 8e-07, + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/deepseek-v3-0324": { - "input_cost_per_token": 2e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-ai/DeepSeek-V4-Pro": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1.72e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 5.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/hermes3-405b": { - "input_cost_per_token": 8e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1.72e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 8e-07, + "output_cost_per_token": 5.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/hermes3-70b": { - "input_cost_per_token": 1.2e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 1.6e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/hermes3-8b": { - "input_cost_per_token": 2.5e-08, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-chat": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 4e-08, + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/lfm-40b": { - "input_cost_per_token": 1e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 2e-07, + "output_cost_per_token": 1.6e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/lfm-7b": { - "input_cost_per_token": 2.5e-08, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-reasoner": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 4e-08, + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": { - "input_cost_per_token": 5e-08, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, + "inferenceapis/deepseek-v3": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 1e-07, + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama-4-scout-17b-16e-instruct": { - "input_cost_per_token": 5e-08, - "litellm_provider": "lambda_ai", - "max_input_tokens": 16384, - "max_output_tokens": 8192, - "max_tokens": 8192, + "inferenceapis/deepseek-v4-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 1e-07, + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama3.1-405b-instruct-fp8": { - "input_cost_per_token": 8e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-v4-pro": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1.72e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 8e-07, + "output_cost_per_token": 5.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama3.1-70b-instruct-fp8": { - "input_cost_per_token": 1.2e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 1.6e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama3.1-8b-instruct": { - "input_cost_per_token": 2.5e-08, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/glm-5.3": { + "cache_read_input_token_cost": 3.4e-07, + "input_cost_per_token": 1.82e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", - "output_cost_per_token": 4e-08, + "output_cost_per_token": 5.72e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": { - "input_cost_per_token": 1.2e-07, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "inferenceapis/glm-5.3-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 6.6e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama3.2-11b-vision-instruct": { - "input_cost_per_token": 1.5e-08, - "litellm_provider": "lambda_ai", + "inferenceapis/gpt-oss-120b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-08, + "output_cost_per_token": 8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, + "supports_native_streaming": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, - "lambda_ai/llama3.2-3b-instruct": { - "input_cost_per_token": 1.5e-08, - "litellm_provider": "lambda_ai", + "inferenceapis/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-08, + "output_cost_per_token": 1.9e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/llama3.3-70b-instruct-fp8": { - "input_cost_per_token": 1.2e-07, - "litellm_provider": "lambda_ai", + "inferenceapis/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 8.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.42e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/llama-3.1-8b-instant": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/qwen25-coder-32b-instruct": { - "input_cost_per_token": 5e-08, - "litellm_provider": "lambda_ai", + "inferenceapis/llama-3.3-70b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false }, - "lambda_ai/qwen3-32b-fp8": { - "input_cost_per_token": 5e-08, - "litellm_provider": "lambda_ai", + "inferenceapis/llama-3.3-70b-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false }, - "low/1024-x-1024/gpt-image-1": { - "deprecation_date": "2026-10-23", - "input_cost_per_image": 0.011, - "input_cost_per_pixel": 1.0490417e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0, + "inferenceapis/llama-3.3-70b-versatile": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ - "/v1/images/generations" - ] + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false }, - "low/1024-x-1536/gpt-image-1": { - "deprecation_date": "2026-10-23", - "input_cost_per_image": 0.016, - "input_cost_per_pixel": 1.0172526e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0, + "inferenceapis/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ - "/v1/images/generations" - ] + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false }, - "low/1536-x-1024/gpt-image-1": { - "deprecation_date": "2026-10-23", - "input_cost_per_image": 0.016, - "input_cost_per_pixel": 1.0172526e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0, + "inferenceapis/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ - "/v1/images/generations" - ] + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false }, - "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { - "litellm_provider": "bedrock", - "max_input_tokens": 77, - "max_tokens": 77, - "mode": "image_generation", - "output_cost_per_image": 0.036 + "inferenceapis/minimax-m3": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 3.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 1.56e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { - "litellm_provider": "bedrock", - "max_input_tokens": 77, - "max_tokens": 77, - "mode": "image_generation", - "output_cost_per_image": 0.072 + "inferenceapis/MiniMaxAI/MiniMax-M3": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 3.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 1.56e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "medium/1024-x-1024/gpt-image-1": { - "deprecation_date": "2026-10-23", - "input_cost_per_image": 0.042, - "input_cost_per_pixel": 4.0054321e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0, + "inferenceapis/moonshotai/Kimi-K2.7-Code": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 8.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.42e-06, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ - "/v1/images/generations" - ] + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "medium/1024-x-1536/gpt-image-1": { - "deprecation_date": "2026-10-23", - "input_cost_per_image": 0.063, - "input_cost_per_pixel": 4.0054321e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0, + "inferenceapis/openai/gpt-oss-120b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ - "/v1/images/generations" - ] + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "medium/1536-x-1024/gpt-image-1": { - "deprecation_date": "2026-10-23", - "input_cost_per_image": 0.063, - "input_cost_per_pixel": 4.0054321e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0, + "inferenceapis/openai/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.9e-07, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ - "/v1/images/generations" - ] + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "low/1024-x-1024/gpt-image-1-mini": { - "deprecation_date": "2026-12-01", - "input_cost_per_image": 0.005, - "litellm_provider": "openai", - "mode": "image_generation", + "inferenceapis/Qwen/Qwen3-VL-235B-A22B-Instruct": { + "input_cost_per_token": 2.6e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ - "/v1/images/generations" - ] + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": true }, - "low/1024-x-1536/gpt-image-1-mini": { - "deprecation_date": "2026-12-01", - "input_cost_per_image": 0.006, - "litellm_provider": "openai", - "mode": "image_generation", + "inferenceapis/Qwen/Qwen3.8-Flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ - "/v1/images/generations" - ] + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "low/1536-x-1024/gpt-image-1-mini": { - "deprecation_date": "2026-12-01", - "input_cost_per_image": 0.006, - "litellm_provider": "openai", - "mode": "image_generation", + "inferenceapis/qwen3-vl": { + "input_cost_per_token": 2.6e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ - "/v1/images/generations" - ] + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": true }, - "medium/1024-x-1024/gpt-image-1-mini": { - "deprecation_date": "2026-12-01", - "input_cost_per_image": 0.011, - "litellm_provider": "openai", - "mode": "image_generation", + "inferenceapis/qwen3-vl-235b": { + "input_cost_per_token": 2.6e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ - "/v1/images/generations" - ] + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": true }, - "medium/1024-x-1536/gpt-image-1-mini": { - "deprecation_date": "2026-12-01", - "input_cost_per_image": 0.015, - "litellm_provider": "openai", - "mode": "image_generation", + "inferenceapis/qwen3.8-flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ - "/v1/images/generations" - ] + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "medium/1536-x-1024/gpt-image-1-mini": { - "deprecation_date": "2026-12-01", - "input_cost_per_image": 0.015, - "litellm_provider": "openai", - "mode": "image_generation", + "inferenceapis/zai-org/GLM-5.3": { + "cache_read_input_token_cost": 3.4e-07, + "input_cost_per_token": 1.82e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_output_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 5.72e-06, + "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ - "/v1/images/generations" - ] + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "medlm-large": { - "input_cost_per_character": 5e-06, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, + "inferenceapis/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", - "output_cost_per_character": 1.5e-05, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true + "output_cost_per_token": 6.6e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, - "medlm-medium": { - "input_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 32768, + "text-completion-inception/mercury-edit-2": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "text-completion-inception", + "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 7.5e-07 + }, + "lambda_ai/deepseek-llama3.3-70b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_character": 1e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "meta.llama2-13b-chat-v1": { - "input_cost_per_token": 7.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "lambda_ai/deepseek-r1-0528": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "meta.llama2-70b-chat-v1": { - "input_cost_per_token": 1.95e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "lambda_ai/deepseek-r1-671b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.56e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "meta.llama3-1-405b-instruct-v1:0": { - "input_cost_per_token": 2.4e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "lambda_ai/deepseek-v3-0324": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.4e-06, - "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", + "output_cost_per_token": 6e-07, "supports_function_calling": true, - "supports_tool_choice": false + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "meta.llama3-1-70b-instruct-v1:0": { - "deprecation_date": "2027-03-30", - "input_cost_per_token": 7.2e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "lambda_ai/hermes3-405b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", - "output_cost_per_token": 7.2e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-1-70b-instruct.md", + "output_cost_per_token": 8e-07, "supports_function_calling": true, - "supports_tool_choice": false - }, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/hermes3-70b": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/hermes3-8b": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/lfm-40b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/lfm-7b": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 16384, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-405b-instruct-fp8": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-8b-instruct": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.2-11b-vision-instruct": { + "input_cost_per_token": 1.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "lambda_ai/llama3.2-3b-instruct": { + "input_cost_per_token": 1.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.3-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/qwen25-coder-32b-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/qwen3-32b-fp8": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "low/1024-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.011, + "input_cost_per_pixel": 1.0490417e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1024-x-1536/gpt-image-1": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.016, + "input_cost_per_pixel": 1.0172526e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1536-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.016, + "input_cost_per_pixel": 1.0172526e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.036 + }, + "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.072 + }, + "medium/1024-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.042, + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1024-x-1536/gpt-image-1": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.063, + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1536-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.063, + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1024-x-1024/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.005, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1024-x-1536/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.006, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1536-x-1024/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.006, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1024-x-1024/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.011, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1024-x-1536/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.015, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1536-x-1024/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", + "input_cost_per_image": 0.015, + "litellm_provider": "openai", + "mode": "image_generation", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medlm-large": { + "input_cost_per_character": 5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 1.5e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "medlm-medium": { + "input_cost_per_character": 5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 1e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "meta.llama2-13b-chat-v1": { + "input_cost_per_token": 7.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "meta.llama2-70b-chat-v1": { + "input_cost_per_token": 1.95e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.56e-06, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "meta.llama3-1-405b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-1-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_function_calling": true, + "supports_tool_choice": false + }, "meta.llama3-1-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.2e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-1-8b-instruct.md", + "output_cost_per_token_batches": 1.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-2-11b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.6e-07, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -38797,33 +42578,38 @@ "supports_vision": true }, "meta.llama3-2-1b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-2-3b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-2-90b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -38833,47 +42619,49 @@ }, "meta.llama3-3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-3-70b-instruct.md", + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "meta.llama4-maverick-17b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md", "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9.7e-07, "output_cost_per_token_batches": 4.85e-07, @@ -38891,12 +42679,12 @@ }, "meta.llama4-scout-17b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md", "input_cost_per_token": 1.7e-07, "input_cost_per_token_batches": 8.5e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 10000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_batches": 3.3e-07, @@ -38912,13 +42700,58 @@ "supports_function_calling": true, "supports_tool_choice": false }, + "meta/muse-ember-1.0": { + "cache_read_input_token_cost": 4e-09, + "cache_read_input_token_cost_above_200k_tokens": 1.2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_200k_tokens": 3e-07, + "litellm_provider": "meta", + "max_input_tokens": 1048576, + "max_output_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_200k_tokens": 1.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://dev.meta.ai/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "meta/muse-spark-1.1": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.25e-06, "search_context_cost_per_query": { @@ -38959,7 +42792,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.25e-06, "search_context_cost_per_query": { @@ -39000,7 +42832,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "search_context_cost_per_query": { @@ -39041,7 +42872,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.25e-06, "search_context_cost_per_query": { @@ -39082,7 +42912,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "search_context_cost_per_query": { @@ -39139,7 +42968,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-05, "search_context_cost_per_query": { @@ -39180,7 +43008,6 @@ "litellm_provider": "meta_llama", "max_input_tokens": 128000, "max_output_tokens": 4028, - "max_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ @@ -39196,7 +43023,6 @@ "litellm_provider": "meta_llama", "max_input_tokens": 128000, "max_output_tokens": 4028, - "max_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ @@ -39212,7 +43038,6 @@ "litellm_provider": "meta_llama", "max_input_tokens": 1000000, "max_output_tokens": 4028, - "max_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ @@ -39229,7 +43054,6 @@ "litellm_provider": "meta_llama", "max_input_tokens": 10000000, "max_output_tokens": 4028, - "max_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ @@ -39244,16 +43068,20 @@ }, "minimax.minimax-m2": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2.html", + "output_cost_per_token_priority": 2.1e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -39263,37 +43091,44 @@ }, "minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 196000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 196000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -39423,36 +43258,121 @@ "max_input_tokens": 1000000, "max_output_tokens": 128000 }, + "minimax/MiniMax-M3.1-Flash": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 1.5e-08, + "litellm_provider": "minimax", + "mode": "chat", + "source": "https://platform.minimax.io/docs/guides/pricing-paygo", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "xhigh", + "max" + ], + "supports_vision": true, + "max_input_tokens": 1000000 + }, + "minimax/minimax-latest": { + "alias_of": "minimax/MiniMax-M3" + }, + "minimax/MiniMax-H3": { + "litellm_provider": "minimax", + "mode": "video_generation", + "source": "https://platform.minimax.io/docs/guides/pricing-paygo", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "output_cost_per_second_2k": 0.13, + "input_cost_per_image": 0.04, + "provider_specific_entry": { + "minimax_free_input_images": 5 + }, + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "metadata": { + "comment": "V2 async task API. Pay-as-you-go list price $0.08/s at 768P and $0.13/s at 2K, plus $0.04 per input image beyond the first 5. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call." + } + }, + "minimax/MiniMax-H3-Max": { + "litellm_provider": "minimax", + "mode": "video_generation", + "source": "https://platform.minimax.io/docs/guides/pricing-paygo", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "input_cost_per_image": 0.074, + "provider_specific_entry": { + "minimax_free_input_images": 2 + }, + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "metadata": { + "comment": "V2 async task API, fast tier. Pay-as-you-go list price $0.05/s at 480P and $0.08/s at 768P; no 2K. Plus $0.074 per input image beyond the first 2. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call." + } + }, "mistral.devstral-2-123b": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, "input_cost_per_token_flex": 2e-07, + "input_cost_per_token_priority": 7e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, "output_cost_per_token_flex": 1e-06, + "output_cost_per_token_priority": 3.5e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-devstral-2-123b.html", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "mistral.magistral-small-2509": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 8.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 40000, - "max_tokens": 40000, "mode": "chat", "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_priority": 2.63e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, @@ -39462,15 +43382,18 @@ }, "mistral.ministral-3-14b-instruct": { "input_cost_per_token": 2e-07, + "input_cost_per_token_batches": 1e-07, "input_cost_per_token_flex": 1e-07, + "input_cost_per_token_priority": 3.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2e-07, + "output_cost_per_token_batches": 1e-07, "output_cost_per_token_flex": 1e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_priority": 3.5e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -39480,15 +43403,18 @@ }, "mistral.ministral-3-3b-instruct": { "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.7e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-07, + "output_cost_per_token_batches": 5e-08, "output_cost_per_token_flex": 5e-08, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_priority": 1.7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -39498,15 +43424,18 @@ }, "mistral.ministral-3-8b-instruct": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7e-08, "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-07, + "output_cost_per_token_batches": 7e-08, "output_cost_per_token_flex": 7e-08, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_priority": 2.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -39516,11 +43445,11 @@ }, "mistral.mistral-7b-instruct-v0:2": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", @@ -39531,7 +43460,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", @@ -39542,7 +43470,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -39551,15 +43478,18 @@ }, "mistral.mistral-large-3-675b-instruct": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 8.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_priority": 2.63e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -39573,7 +43503,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, @@ -39582,11 +43511,11 @@ }, "mistral.mixtral-8x7b-instruct-v0:1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", @@ -39594,58 +43523,184 @@ }, "mistral.voxtral-mini-3b-2507": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 4e-08, + "input_cost_per_token_batches": 2e-08, "input_cost_per_token_flex": 2e-08, + "input_cost_per_token_priority": 7e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-08, + "output_cost_per_token_batches": 2e-08, "output_cost_per_token_flex": 2e-08, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-voxtral-mini-3b-2507.html", + "output_cost_per_token_priority": 7e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true }, "mistral.voxtral-small-24b-2507": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.7e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-07, + "output_cost_per_token_batches": 1.5e-07, "output_cost_per_token_flex": 1.5e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-voxtral-small-24b-2507.html", + "output_cost_per_token_priority": 5.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true }, - "mistral/codestral-2508": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "bedrock/ap-southeast-2/mistral.voxtral-mini-3b-2507": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 4.12e-08, + "input_cost_per_token_batches": 2.06e-08, + "input_cost_per_token_flex": 2.06e-08, + "input_cost_per_token_priority": 7.21e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 32768, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 9e-07, - "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 4.12e-08, + "output_cost_per_token_batches": 2.06e-08, + "output_cost_per_token_flex": 2.06e-08, + "output_cost_per_token_priority": 7.21e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-southeast-2/index.json", + "supports_audio_input": true, + "supports_system_messages": true, + "supports_native_structured_output": true }, - "mistral/codestral-latest": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "bedrock/ap-southeast-2/mistral.voxtral-small-24b-2507": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 1.03e-07, + "input_cost_per_token_batches": 5.15e-08, + "input_cost_per_token_flex": 5.15e-08, + "input_cost_per_token_priority": 1.8025e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.09e-07, + "output_cost_per_token_batches": 1.545e-07, + "output_cost_per_token_flex": 1.545e-07, + "output_cost_per_token_priority": 5.4075e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-southeast-2/index.json", + "supports_audio_input": true, + "supports_system_messages": true, + "supports_native_structured_output": true + }, + "bedrock/ap-northeast-1/mistral.voxtral-mini-3b-2507": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 5e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 9e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-08, + "output_cost_per_token_batches": 3e-08, + "output_cost_per_token_flex": 3e-08, + "output_cost_per_token_priority": 9e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-northeast-1/index.json", + "supports_audio_input": true, + "supports_system_messages": true, + "supports_native_structured_output": true + }, + "bedrock/ap-northeast-1/mistral.voxtral-small-24b-2507": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 1.2e-07, + "input_cost_per_token_batches": 6e-08, + "input_cost_per_token_flex": 6e-08, + "input_cost_per_token_priority": 2.1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.6e-07, + "output_cost_per_token_batches": 1.8e-07, + "output_cost_per_token_flex": 1.8e-07, + "output_cost_per_token_priority": 6.3e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-northeast-1/index.json", + "supports_audio_input": true, + "supports_system_messages": true, + "supports_native_structured_output": true + }, + "bedrock/eu-west-2/mistral.voxtral-mini-3b-2507": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-08, + "output_cost_per_token_batches": 3e-08, + "output_cost_per_token_flex": 3e-08, + "output_cost_per_token_priority": 1.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/eu-west-2/index.json", + "supports_audio_input": true, + "supports_system_messages": true, + "supports_native_structured_output": true + }, + "bedrock/eu-west-2/mistral.voxtral-small-24b-2507": { + "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "input_cost_per_token": 1.6e-07, + "input_cost_per_token_batches": 8e-08, + "input_cost_per_token_flex": 8e-08, + "input_cost_per_token_priority": 2.8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "output_cost_per_token_batches": 2.3e-07, + "output_cost_per_token_flex": 2.3e-07, + "output_cost_per_token_priority": 8.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/eu-west-2/index.json", + "supports_audio_input": true, + "supports_system_messages": true, + "supports_native_structured_output": true + }, + "mistral/codestral-2508": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/codestral-latest": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", @@ -39660,7 +43715,6 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://mistral.ai/technology/", @@ -39673,12 +43727,16 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 3e-07, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, @@ -39688,12 +43746,16 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://mistral.ai/news/devstral-2-vibe-cli", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, @@ -39703,12 +43765,16 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://mistral.ai/news/devstral-2-vibe-cli", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, @@ -39717,7 +43783,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", @@ -39733,7 +43798,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", @@ -39749,7 +43813,6 @@ "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", @@ -39765,7 +43828,6 @@ "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", @@ -39780,7 +43842,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "source": "https://docs.mistral.ai/models/mistral-embed-23-12" }, @@ -39790,7 +43851,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -39837,13 +43897,140 @@ ], "supports_audio_output": true }, + "mistral/voxtral-mini-transcribe-3": { + "input_cost_per_second": 5.83333e-05, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/voxtral-mini-transcribe-3-0", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "mistral/voxtral-mini-transcribe-3-0": { + "input_cost_per_second": 5.83333e-05, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/voxtral-mini-transcribe-3-0", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "mistral/voxtral-small-transcribe-3": { + "input_cost_per_second": 6.66667e-05, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/voxtral-small-transcribe-3-0", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "mistral/voxtral-small-transcribe-3-0": { + "input_cost_per_second": 6.66667e-05, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/voxtral-small-transcribe-3-0", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "mistral/voxtral-mini-transcribe-realtime-3": { + "input_cost_per_second": 0.000133333, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/voxtral-mini-transcribe-realtime-3-0", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "mistral/voxtral-mini-transcribe-realtime-3-0": { + "input_cost_per_second": 0.000133333, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/voxtral-mini-transcribe-realtime-3-0", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "mistral/voxtral-mini-tts-3": { + "input_cost_per_character": 1.3e-05, + "litellm_provider": "mistral", + "mode": "audio_speech", + "source": "https://docs.mistral.ai/models/voxtral-mini-tts-3-0", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": true + }, + "mistral/voxtral-mini-tts-3-0": { + "input_cost_per_character": 1.3e-05, + "litellm_provider": "mistral", + "mode": "audio_speech", + "source": "https://docs.mistral.ai/models/voxtral-mini-tts-3-0", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": true + }, "mistral/voxtral-small-2507": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://docs.mistral.ai/models/voxtral-small-25-07", @@ -39858,7 +44045,6 @@ "litellm_provider": "mistral", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://docs.mistral.ai/models/voxtral-small-25-07", @@ -39870,11 +44056,11 @@ "mistral/zai-glm-5-2": { "cache_read_input_token_cost": 1.4e-07, "deprecation_date": "2026-10-31", + "deprecation_source": "https://docs.mistral.ai/getting-started/models/models_overview", "input_cost_per_token": 1.4e-06, "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -39894,13 +44080,29 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "mistral/deepseek-v4-1-flash-1017": { + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://docs.mistral.ai/models/deepseek-v4-flash-1017", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "mistral/zai-glm-5-3": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -39916,13 +44118,34 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "mistral/zai-glm-5-3-flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-3-flash", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "mistral/zai-glm-5": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -39944,7 +44167,6 @@ "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -39966,7 +44188,6 @@ "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -40045,7 +44266,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", @@ -40062,7 +44282,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", @@ -40077,7 +44296,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding" }, "mistral/codestral-embed": { @@ -40085,7 +44303,6 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding" }, "mistral/codestral-embed-2505": { @@ -40093,22 +44310,21 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding" }, "mistral/mistral-large-4": { - "cache_read_input_token_cost": 6.8e-08, - "input_cost_per_token": 6.8e-07, + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 7e-07, "litellm_provider": "mistral", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 2.09e-06, + "output_cost_per_token": 2.1e-06, "reasoning_effort_levels": [ "none", "high" ], - "source": "https://docs.mistral.ai/models/mistral-large-4", + "source": "https://docs.mistral.ai/models/mistral-large-4-0", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -40118,18 +44334,18 @@ "supports_vision": true }, "mistral/mistral-large-4-0": { - "cache_read_input_token_cost": 6.8e-08, - "input_cost_per_token": 6.8e-07, + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 7e-07, "litellm_provider": "mistral", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 2.09e-06, + "output_cost_per_token": 2.1e-06, "reasoning_effort_levels": [ "none", "high" ], - "source": "https://docs.mistral.ai/models/mistral-large-4", + "source": "https://docs.mistral.ai/models/mistral-large-4-0", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -40144,7 +44360,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", @@ -40160,7 +44375,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", @@ -40171,12 +44385,12 @@ "supports_vision": true }, "mistral/mistral-large-2512": { + "deprecation_date": "2027-04-30", "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", @@ -40192,7 +44406,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -40213,7 +44426,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -40234,7 +44446,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -40250,12 +44461,12 @@ "supports_vision": true }, "mistral/mistral-medium-3-5": { + "deprecation_date": "2027-04-30", "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -40276,11 +44487,15 @@ "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-07, + "reasoning_effort_levels": [ + "none", + "high" + ], "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, @@ -40290,7 +44505,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "reasoning_effort_levels": [ @@ -40311,7 +44525,6 @@ "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://mistral.ai/pricing", @@ -40327,7 +44540,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://mistral.ai/pricing", @@ -40343,7 +44555,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://mistral.ai/pricing", @@ -40359,7 +44570,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://mistral.ai/pricing", @@ -40375,7 +44585,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://mistral.ai/pricing", @@ -40391,7 +44600,6 @@ "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_assistant_prefill": true, @@ -40404,7 +44612,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://mistral.ai/technology/", @@ -40418,7 +44625,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_assistant_prefill": true, @@ -40429,14 +44635,18 @@ }, "moonshot.kimi-k2-thinking": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.38e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, @@ -40447,19 +44657,22 @@ }, "moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.25e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true }, @@ -40469,7 +44682,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://platform.kimi.ai/docs/pricing/chat-k27-code", @@ -40483,11 +44695,11 @@ }, "moonshot/kimi-k2.5": { "cache_read_input_token_cost": 1e-07, + "deprecation_date": "2026-08-31", "input_cost_per_token": 6e-07, "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", @@ -40504,7 +44716,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://platform.kimi.ai/docs/pricing/chat-k26", @@ -40515,13 +44726,58 @@ "supports_video_input": true, "supports_vision": true }, + "moonshot/kimi-k3.1-pro": { + "cache_creation_input_token_cost": 2e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://platform.kimi.ai/docs/pricing/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "moonshot/kimi-k3.1-pro-highspeed": { + "cache_creation_input_token_cost": 0.000004, + "cache_creation_input_token_cost_above_1hr": 0.000008, + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000004, + "litellm_provider": "moonshot", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 0.00002, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://platform.kimi.ai/docs/pricing/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, "moonshot/kimi-k3": { + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "moonshot", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ @@ -40531,18 +44787,22 @@ ], "source": "https://platform.kimi.ai/docs/pricing/chat-k3", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, + "moonshot/kimi-latest": { + "alias_of": "moonshot/kimi-k3" + }, "moonshot/moonshot-v1-128k": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -40551,11 +44811,11 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-128k-vision-preview": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -40565,11 +44825,11 @@ "supports_vision": true }, "moonshot/moonshot-v1-32k": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -40578,11 +44838,11 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-32k-vision-preview": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -40592,11 +44852,11 @@ "supports_vision": true }, "moonshot/moonshot-v1-8k": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -40605,11 +44865,11 @@ "supports_tool_choice": true }, "moonshot/moonshot-v1-8k-vision-preview": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -40619,11 +44879,11 @@ "supports_vision": true }, "moonshot/moonshot-v1-auto": { + "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -40631,12 +44891,137 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "morph/morph-kimik3": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.4e-05, + "cache_read_input_token_cost": 2.9e-07, + "litellm_provider": "morph", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing", + "supports_vision": true + }, + "morph/morph-kimik3-fast": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 6e-06, + "output_cost_per_token": 2.25e-05, + "cache_read_input_token_cost": 6e-07, + "litellm_provider": "morph", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing", + "supports_vision": true + }, + "morph/morph-glm53-744b": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.19e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 1.955e-07, + "litellm_provider": "morph", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing" + }, + "morph/morph-glm53flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 7e-07, + "cache_read_input_token_cost": 4e-08, + "litellm_provider": "morph", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing", + "supports_vision": true + }, + "morph/morph-dsv41flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 8e-07, + "cache_read_input_token_cost": 8e-09, + "litellm_provider": "morph", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing", + "supports_vision": true + }, + "morph/morph-dsv41flash-1017": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 8e-07, + "cache_read_input_token_cost": 8e-09, + "litellm_provider": "morph", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing", + "supports_vision": true + }, + "morph/morph-dsv41flash-abliterated": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "morph", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing", + "supports_vision": true + }, + "morph/morph-dsv4flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.41953125e-07, + "output_cost_per_token": 3.99625e-07, + "cache_read_input_token_cost": 3.59375e-08, + "litellm_provider": "morph", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.morphllm.com/pricing" + }, "morph/morph-v3-fast": { "input_cost_per_token": 8e-07, "litellm_provider": "morph", "max_input_tokens": 16000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": false, @@ -40650,7 +45035,6 @@ "litellm_provider": "morph", "max_input_tokens": 16000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 1.9e-06, "supports_function_calling": false, @@ -40668,7 +45052,6 @@ "input_cost_per_video_per_second_above_8s_interval": 0.001, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -40680,10 +45063,12 @@ "text", "image", "video" - ] + ], + "supports_embedding_image_input": true }, "multimodalembedding@001": { "deprecation_date": "2027-04-01", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "input_cost_per_character": 2e-07, "input_cost_per_image": 0.0001, "input_cost_per_token": 8e-07, @@ -40692,7 +45077,6 @@ "input_cost_per_video_per_second_above_8s_interval": 0.001, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -40704,7 +45088,8 @@ "text", "image", "video" - ] + ], + "supports_embedding_image_input": true }, "nscale/Qwen/QwQ-32B": { "input_cost_per_token": 1.8e-07, @@ -40852,7 +45237,6 @@ ] }, "nebius/deepseek-ai/DeepSeek-R1": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 8e-07, @@ -40864,7 +45248,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 164000, "max_input_tokens": 164000, "max_output_tokens": 164000, "input_cost_per_token": 8e-07, @@ -40876,7 +45259,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2.5e-07, @@ -40887,7 +45269,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-V3": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 5e-07, @@ -40898,7 +45279,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 5e-07, @@ -40909,7 +45289,6 @@ "source": "https://nebius.com/prices" }, "nebius/google/gemma-3-27b-it": { - "max_tokens": 110000, "max_input_tokens": 110000, "max_output_tokens": 110000, "input_cost_per_token": 1e-07, @@ -40918,10 +45297,10 @@ "mode": "chat", "supports_function_calling": true, "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/google%2Fgemma-3-27b-it" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 4e-08 }, "nebius/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, @@ -40932,7 +45311,6 @@ "source": "https://nebius.com/prices" }, "nebius/meta-llama/Llama-Guard-3-8B": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-08, @@ -40942,7 +45320,6 @@ "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-08, @@ -40953,7 +45330,6 @@ "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.3e-07, @@ -40964,7 +45340,6 @@ "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1e-06, @@ -40975,7 +45350,6 @@ "source": "https://nebius.com/prices" }, "nebius/mistralai/Mistral-Nemo-Instruct-2407": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 4e-08, @@ -40986,7 +45360,6 @@ "source": "https://nebius.com/prices" }, "nebius/NousResearch/Hermes-3-Llama-3.1-405B": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1e-06, @@ -40997,7 +45370,6 @@ "source": "https://nebius.com/prices" }, "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 6e-07, @@ -41008,7 +45380,6 @@ "source": "https://nebius.com/prices" }, "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -41019,7 +45390,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-235B-A22B": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-07, @@ -41030,7 +45400,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-32B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-07, @@ -41041,7 +45410,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-32B" }, "nebius/Qwen/Qwen3-30B-A3B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -41052,7 +45420,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-14B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 8e-08, @@ -41063,7 +45430,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-4B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 8e-08, @@ -41074,7 +45440,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/QwQ-32B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.5e-07, @@ -41086,7 +45451,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-72B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.3e-07, @@ -41097,7 +45461,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-32B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 6e-08, @@ -41108,7 +45471,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-Coder-7B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-08, @@ -41119,7 +45481,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-VL-72B-Instruct": { - "max_tokens": 32000, "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 2.5e-07, @@ -41131,7 +45492,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/image2text/Qwen%2FQwen2.5-VL-72B-Instruct" }, "nebius/Qwen/Qwen2-VL-72B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, @@ -41143,7 +45503,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2-VL-7B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, @@ -41154,7 +45513,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-V4-Flash": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.4e-07, @@ -41166,8 +45524,7 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash" }, "nebius/deepseek-ai/DeepSeek-V4-Flash-0731": { - "max_tokens": 1024000, - "max_input_tokens": 1024000, + "max_input_tokens": 1048576, "max_output_tokens": 1024000, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, @@ -41175,10 +45532,10 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash-0731" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1e-08 }, "nebius/deepseek-ai/DeepSeek-V4-Pro": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.75e-06, @@ -41187,33 +45544,34 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.4e-07 }, "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { "input_cost_per_token": 1.32e-06, "litellm_provider": "nebius", - "max_input_tokens": 979000, + "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.96e-06, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro-0813", + "source": "https://tokenfactory.nebius.com/api/public/models_info", "supports_function_calling": true, - "supports_reasoning": true + "supports_reasoning": true, + "cache_read_input_token_cost": 4e-08 }, "nebius/deepseek-ai/DeepSeek-V4.1-Flash": { "input_cost_per_token": 3e-07, "litellm_provider": "nebius", - "max_input_tokens": 1048000, + "max_input_tokens": 1048576, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://tokenfactory.nebius.com/endpoints?modals=endpoint-details&model-id=deepseek-ai/DeepSeek-V4.1-Flash", + "source": "https://tokenfactory.nebius.com/api/public/models_info", "supports_function_calling": true, "supports_reasoning": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1e-08 }, "nebius/MiniMaxAI/MiniMax-M2.5": { - "max_tokens": 196608, "max_input_tokens": 196608, "max_output_tokens": 196608, "input_cost_per_token": 3e-07, @@ -41225,7 +45583,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M2.5" }, "nebius/MiniMaxAI/MiniMax-M3": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 3e-07, @@ -41235,10 +45592,10 @@ "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M3" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 6e-08 }, "nebius/moonshotai/Kimi-K2.6": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9.5e-07, @@ -41248,10 +45605,10 @@ "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K2.6" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.6e-07 }, "nebius/moonshotai/Kimi-K2.7-Code": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9.5e-07, @@ -41261,11 +45618,23 @@ "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/moonshotai%2FKimi-K2.7-Code" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.5e-07 + }, + "nebius/moonshotai/Kimi-K3.1-Pro": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info" }, "nebius/moonshotai/Kimi-K3": { - "max_tokens": 1024000, - "max_input_tokens": 1024000, + "max_input_tokens": 1048576, "max_output_tokens": 1024000, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, @@ -41274,10 +45643,10 @@ "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K3" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 3e-07 }, "nebius/NousResearch/Hermes-4-405B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-06, @@ -41286,10 +45655,10 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-405B" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 2e-07 }, "nebius/NousResearch/Hermes-4-70B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, @@ -41301,7 +45670,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-70B" }, "nebius/nvidia/Cosmos3-Super-Reasoner": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-07, @@ -41314,7 +45682,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/image2text/nvidia%2FCosmos3-Super-Reasoner" }, "nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6e-07, @@ -41325,7 +45692,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FLlama-3_1-Nemotron-Ultra-253B-v1" }, "nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 6e-08, @@ -41334,10 +45700,10 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNVIDIA-Nemotron-3-Nano-30B-A3B" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.2e-08 }, "nebius/nvidia/Nemotron-3-Nano-Omni": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 6e-08, @@ -41350,7 +45716,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Nano-Omni" }, "nebius/nvidia/nemotron-3-super-120b-a12b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-07, @@ -41359,10 +45724,10 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2Fnemotron-3-super-120b-a12b" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 6e-08 }, "nebius/nvidia/Nemotron-3-Ultra-550b-a55b": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1e-06, @@ -41371,10 +45736,10 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Ultra-550b-a55b" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.2e-07 }, "nebius/nvidia/Nemotron-3_5-Lightning": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 6e-08, @@ -41383,10 +45748,10 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3_5-Lightning" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 3e-08 }, "nebius/openai/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, @@ -41395,10 +45760,10 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/openai%2Fgpt-oss-120b" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1e-07 }, "nebius/openbmb/MiniCPM-V-4_5": { - "max_tokens": 32000, "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 6.58e-07, @@ -41406,10 +45771,10 @@ "litellm_provider": "nebius", "mode": "chat", "supports_vision": true, - "source": "https://tokenfactory.nebius.com/models/catalog/image2text/openbmb%2FMiniCPM-V-4_5" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.3e-07 }, "nebius/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-07, @@ -41417,10 +45782,10 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-235B-A22B-Instruct-2507" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 5e-08 }, "nebius/Qwen/Qwen3-30B-A3B-Instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-07, @@ -41428,10 +45793,10 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-30B-A3B-Instruct-2507" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1e-07 }, "nebius/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.5e-07, @@ -41443,7 +45808,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-Next-80B-A3B-Thinking" }, "nebius/Qwen/Qwen3.5-397B-A17B": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 6e-07, @@ -41452,7 +45816,8 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.5-397B-A17B" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.2e-07 }, "nebius/Qwen/Qwen3.8-27B": { "input_cost_per_token": 4.5e-07, @@ -41460,12 +45825,12 @@ "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.8-27B", + "source": "https://tokenfactory.nebius.com/api/public/models_info", "supports_function_calling": true, - "supports_reasoning": true + "supports_reasoning": true, + "cache_read_input_token_cost": 1e-07 }, "nebius/zai-org/GLM-5.1": { - "max_tokens": 202752, "max_input_tokens": 202752, "max_output_tokens": 202752, "input_cost_per_token": 1.4e-06, @@ -41474,10 +45839,10 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.1" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 2.6e-07 }, "nebius/zai-org/GLM-5.2": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.4e-06, @@ -41486,22 +45851,23 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.2" + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "cache_read_input_token_cost": 1.4e-07 }, "nebius/zai-org/GLM-5.3": { "input_cost_per_token": 1.4e-06, "litellm_provider": "nebius", - "max_input_tokens": 1024000, - "max_tokens": 1024000, + "max_input_tokens": 1048576, + "max_output_tokens": 1024000, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3", + "source": "https://tokenfactory.nebius.com/api/public/models_info", "supports_function_calling": true, - "supports_reasoning": true + "supports_reasoning": true, + "cache_read_input_token_cost": 2.6e-07 }, "nebius/zai-org/GLM-5.3-Flash": { - "max_tokens": 1024000, - "max_input_tokens": 1024000, + "max_input_tokens": 1048576, "max_output_tokens": 1024000, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, @@ -41509,11 +45875,11 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3-Flash", - "supports_vision": true + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "supports_vision": true, + "cache_read_input_token_cost": 3e-08 }, "nebius/BAAI/bge-en-icl": { - "max_tokens": 32768, "max_input_tokens": 32768, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -41522,7 +45888,6 @@ "source": "https://nebius.com/prices" }, "nebius/BAAI/bge-multilingual-gemma2": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -41531,7 +45896,6 @@ "source": "https://nebius.com/prices" }, "nebius/intfloat/e5-mistral-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -41540,7 +45904,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-Embedding-8B": { - "max_tokens": 40960, "max_input_tokens": 40960, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -41550,16 +45913,20 @@ }, "nvidia.nemotron-nano-12b-v2": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2e-07, + "input_cost_per_token_batches": 1e-07, "input_cost_per_token_flex": 1e-07, + "input_cost_per_token_priority": 3.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, "output_cost_per_token_flex": 3e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, @@ -41568,16 +45935,20 @@ }, "nvidia.nemotron-nano-9b-v2": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.3e-07, + "output_cost_per_token_batches": 1.2e-07, "output_cost_per_token_flex": 1.2e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", + "output_cost_per_token_priority": 4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, @@ -41586,18 +45957,21 @@ }, "nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.4e-07, + "output_cost_per_token_batches": 1.2e-07, "output_cost_per_token_flex": 1.2e-07, + "output_cost_per_token_priority": 4.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_native_structured_output": true, "supports_response_schema": true, @@ -41605,15 +45979,18 @@ }, "nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 6.5e-07, + "output_cost_per_token_batches": 3.25e-07, "output_cost_per_token_flex": 3.25e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_priority": 1.1375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, @@ -41625,14 +46002,16 @@ "o1": { "cache_read_input_token_cost": 7.5e-06, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -41648,14 +46027,16 @@ "o1-2024-12-17": { "cache_read_input_token_cost": 7.5e-06, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -41670,14 +46051,16 @@ }, "o1-pro": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 0.00015, "input_cost_per_token_batches": 7.5e-05, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.0006, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 0.0003, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ @@ -41704,14 +46087,16 @@ }, "o1-pro-2025-03-19": { "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 0.00015, "input_cost_per_token_batches": 7.5e-05, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.0006, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 0.0003, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ @@ -41740,6 +46125,8 @@ "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "cache_read_input_token_cost_priority": 8.75e-07, + "deprecation_date": "2026-12-11", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, @@ -41747,123 +46134,143 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_flex": 4e-06, "output_cost_per_token_priority": 1.4e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/responses", - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "o3-deep-research": { - "cache_read_input_token_cost": 2.5e-06, - "input_cost_per_token": 1e-05, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 4e-05, - "source": "https://developers.openai.com/api/docs/models/o3-deep-research", - "supported_endpoints": [ - "/v1/batch", - "/v1/responses" + "reasoning_contexts": [ + "auto", + "current_turn" ], - "supported_modalities": [ - "text", - "image" + "reasoning_modes": [ + "standard" + ], + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/responses", + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "o3-deep-research": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "fedramp_uplift_multiplier": 1.1, + "source": "https://developers.openai.com/api/docs/models/o3-deep-research", + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_pdf_input": true, + "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol" + }, + "o3-deep-research-2025-06-26": { + "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "fedramp_uplift_multiplier": 1.1, + "source": "https://developers.openai.com/api/docs/models/o3-deep-research", + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_pdf_input": true + }, + "o3-2025-04-16": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "fedramp_uplift_multiplier": 1.1, + "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_flex": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "standard" ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_pdf_input": true, - "deprecation_date": "2026-07-23" - }, - "o3-deep-research-2025-06-26": { - "deprecation_date": "2026-07-23", - "cache_read_input_token_cost": 2.5e-06, - "input_cost_per_token": 1e-05, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 4e-05, - "source": "https://developers.openai.com/api/docs/models/o3-deep-research", - "supported_endpoints": [ - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_pdf_input": true - }, - "o3-2025-04-16": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_flex": 2.5e-07, - "cache_read_input_token_cost_priority": 8.75e-07, - "deprecation_date": "2026-12-11", - "input_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, - "input_cost_per_token_flex": 1e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 8e-06, - "output_cost_per_token_batches": 4e-06, - "output_cost_per_token_flex": 4e-06, - "output_cost_per_token_priority": 1.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -41896,14 +46303,16 @@ "o3-mini": { "cache_read_input_token_cost": 5.5e-07, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2.2e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -41917,14 +46326,16 @@ "o3-mini-2025-01-31": { "cache_read_input_token_cost": 5.5e-07, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2.2e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, @@ -41936,15 +46347,25 @@ "supports_vision": false }, "o3-pro": { + "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 4e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "pro" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -41974,15 +46395,24 @@ }, "o3-pro-2025-06-10": { "deprecation_date": "2026-12-11", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 4e-05, + "reasoning_contexts": [ + "auto", + "current_turn" + ], + "reasoning_modes": [ + "pro" + ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -42015,6 +46445,8 @@ "cache_read_input_token_cost_flex": 1.38e-07, "cache_read_input_token_cost_priority": 5e-07, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "input_cost_per_token_flex": 5.5e-07, @@ -42022,9 +46454,9 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2.2e-06, "output_cost_per_token_flex": 2.2e-06, "output_cost_per_token_priority": 8e-06, @@ -42050,9 +46482,9 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-06, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", "supported_endpoints": [ "/v1/batch", @@ -42074,18 +46506,22 @@ "supports_tool_choice": false, "supports_vision": true, "supports_pdf_input": true, - "deprecation_date": "2026-07-23" + "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol" }, "o4-mini-deep-research-2025-06-26": { "deprecation_date": "2026-07-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-sol", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-06, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", "supported_endpoints": [ "/v1/batch", @@ -42113,6 +46549,8 @@ "cache_read_input_token_cost_flex": 1.38e-07, "cache_read_input_token_cost_priority": 5e-07, "deprecation_date": "2026-10-23", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "input_cost_per_token_flex": 5.5e-07, @@ -42120,9 +46558,9 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2.2e-06, "output_cost_per_token_flex": 2.2e-06, "output_cost_per_token_priority": 8e-06, @@ -42147,7 +46585,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42160,7 +46597,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42173,7 +46609,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.068e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42186,7 +46621,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42200,7 +46634,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42213,7 +46646,6 @@ "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42227,7 +46659,6 @@ "litellm_provider": "oci", "max_input_tokens": 10485760, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42240,7 +46671,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42253,7 +46683,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42266,7 +46695,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42279,7 +46707,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42292,7 +46719,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42305,7 +46731,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -42318,7 +46743,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -42331,7 +46755,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -42344,7 +46767,6 @@ "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42364,7 +46786,6 @@ "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42383,7 +46804,6 @@ "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42403,7 +46823,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -42417,7 +46836,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -42432,6 +46850,7 @@ "mode": "embedding", "output_vector_size": 1024, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", + "supports_embedding_image_input": true, "supports_vision": true }, "oci/cohere.command-a-reasoning-08-2025": { @@ -42439,7 +46858,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42451,7 +46869,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42464,7 +46881,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 9e-08, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42476,7 +46892,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42488,7 +46903,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42500,7 +46914,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42513,7 +46926,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42525,7 +46937,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42537,7 +46948,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42549,9 +46959,9 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, + "reasoning_effort_levels": [], "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false @@ -42561,19 +46971,79 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, + "oci/xai.grok-4.20-0309-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true + }, + "oci/xai.grok-4.20-0309-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_reasoning": true + }, + "oci/xai.grok-4.20-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true + }, + "oci/xai.grok-4.20-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_reasoning": true + }, "oci/xai.grok-code-fast-1": { "input_cost_per_token": 5e-06, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42585,7 +47055,6 @@ "litellm_provider": "oci", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42600,7 +47069,6 @@ "litellm_provider": "oci", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42615,7 +47083,6 @@ "litellm_provider": "oci", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -42625,11 +47092,34 @@ "supports_response_schema": true, "supports_vision": true }, + "oci/openai.gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true + }, + "oci/openai.gpt-oss-20b": { + "input_cost_per_token": 7e-08, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true + }, "oci/cohere.embed-english-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -42639,7 +47129,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, @@ -42649,7 +47138,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -42659,7 +47147,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, @@ -42669,7 +47156,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -42680,7 +47166,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, @@ -42691,7 +47176,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, @@ -42702,7 +47186,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "oci", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -42714,7 +47197,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": false @@ -42724,7 +47206,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -42733,7 +47214,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -42742,7 +47222,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42752,7 +47231,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42762,7 +47240,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42772,7 +47249,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42782,7 +47258,6 @@ "litellm_provider": "ollama", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42792,7 +47267,6 @@ "litellm_provider": "ollama", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42802,7 +47276,6 @@ "litellm_provider": "ollama", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42812,7 +47285,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42822,7 +47294,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -42831,7 +47302,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -42840,7 +47310,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -42849,7 +47318,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -42858,7 +47326,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -42867,7 +47334,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -42876,7 +47342,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42886,7 +47351,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -42895,7 +47359,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -42904,7 +47367,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42914,7 +47376,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42924,7 +47385,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42934,7 +47394,6 @@ "litellm_provider": "ollama", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42944,7 +47403,6 @@ "litellm_provider": "ollama", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42954,7 +47412,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42964,7 +47421,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -42973,7 +47429,6 @@ "litellm_provider": "ollama", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -42983,7 +47438,6 @@ "litellm_provider": "ollama", "max_input_tokens": 2048, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -42992,7 +47446,6 @@ "litellm_provider": "openai", "max_input_tokens": 32768, "max_output_tokens": 0, - "max_tokens": 0, "mode": "moderation", "output_cost_per_token": 0.0 }, @@ -43001,43 +47454,54 @@ "litellm_provider": "openai", "max_input_tokens": 32768, "max_output_tokens": 0, - "max_tokens": 0, "mode": "moderation", "output_cost_per_token": 0.0 }, "openai.gpt-oss-120b-1:0": { + "supports_vision": false, "supported_endpoints": [ "/v1/chat/completions" ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "openai.gpt-oss-20b-1:0": { + "supports_vision": false, "supported_endpoints": [ "/v1/chat/completions" ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3.5e-08, + "input_cost_per_token_flex": 3.5e-08, + "input_cost_per_token_priority": 1.225e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", + "output_cost_per_token_batches": 1.5e-07, + "output_cost_per_token_flex": 1.5e-07, + "output_cost_per_token_priority": 5.25e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -43045,15 +47509,18 @@ }, "openai.gpt-oss-safeguard-120b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7e-08, "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, "output_cost_per_token_flex": 3e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, @@ -43063,15 +47530,18 @@ }, "openai.gpt-oss-safeguard-20b": { "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3e-08, "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2e-07, + "output_cost_per_token_batches": 1e-07, "output_cost_per_token_flex": 1e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_priority": 3.5e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, @@ -43084,7 +47554,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43098,7 +47567,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43111,7 +47579,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43124,7 +47591,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43137,7 +47603,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 127000, "max_output_tokens": 127000, - "max_tokens": 127000, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43150,7 +47615,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 118000, "max_output_tokens": 118000, - "max_tokens": 118000, "mode": "chat", "output_cost_per_token": 1.3e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43163,7 +47627,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43177,7 +47640,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 6.3e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43190,7 +47652,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 8.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43203,7 +47664,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 9.1e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43217,7 +47677,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.3e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43231,7 +47690,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43245,7 +47703,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43259,7 +47716,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.9e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43273,7 +47729,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.9e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -43281,6 +47736,19 @@ "supports_response_schema": true, "supports_tool_choice": false }, + "parallel_ai/decision": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "parallel_ai", + "max_input_tokens": 32000, + "mode": "evaluation", + "source": "https://docs.parallel.ai/getting-started/pricing#decisions-api", + "supported_endpoints": [ + "/v1/decisions", + "/v1/systemone" + ] + }, "parallel_ai/search": { "input_cost_per_query": 0.005, "litellm_provider": "parallel_ai", @@ -43306,7 +47774,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-06 }, @@ -43315,7 +47782,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -43324,7 +47790,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -43333,7 +47798,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -43342,7 +47806,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07 }, @@ -43351,7 +47814,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -43360,7 +47822,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -43369,7 +47830,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -43379,7 +47839,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -43388,7 +47847,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -43398,7 +47856,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -43418,11 +47875,43 @@ "output_cost_per_token": 0.0, "source": "https://docs.perplexity.ai/docs/getting-started/pricing" }, + "perplexity/pplx-decider-v1.2": { + "input_cost_per_token": 2e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, + "perplexity/pplx-decider-latest": { + "input_cost_per_token": 2e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, + "perplexity/pplx-decider-flash-v1.2": { + "input_cost_per_token": 1e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, + "perplexity/pplx-decider-flash-latest": { + "input_cost_per_token": 1e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, "perplexity/sonar": { "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-06, "search_context_cost_per_query": { @@ -43437,7 +47926,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 8e-06, @@ -43454,7 +47943,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.8e-06 }, @@ -43464,7 +47952,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 12000, "max_output_tokens": 12000, - "max_tokens": 12000, "mode": "chat", "output_cost_per_token": 1.8e-06 }, @@ -43473,7 +47960,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 200000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -43487,7 +47973,7 @@ "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-06, "search_context_cost_per_query": { @@ -43502,7 +47988,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 8e-06, "search_context_cost_per_query": { @@ -43518,7 +48004,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -43528,7 +48013,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 12000, "max_output_tokens": 12000, - "max_tokens": 12000, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -43537,7 +48021,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -43549,7 +48032,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -43561,7 +48043,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -43573,7 +48054,6 @@ "litellm_provider": "publicai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -43585,7 +48065,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -43597,7 +48076,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -43837,7 +48315,6 @@ "input_cost_per_token": 4e-09, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -43847,7 +48324,6 @@ "input_cost_per_token": 3e-08, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560, @@ -43858,7 +48334,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -43870,7 +48345,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -43883,7 +48357,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -43893,11 +48366,11 @@ }, "qwen.qwen3-coder-480b-a35b-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 131072, + "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.8e-06, "supports_function_calling": true, @@ -43912,7 +48385,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 8.8e-07, "output_cost_per_token_flex": 4.4e-07, @@ -43926,14 +48398,18 @@ }, "qwen.qwen3-coder-30b-a3b-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-30b-a3b-instruct.html", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -43941,15 +48417,18 @@ }, "qwen.qwen3-32b-v1:0": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, "output_cost_per_token_flex": 3e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-32b.html", + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -43957,13 +48436,16 @@ }, "qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -43973,13 +48455,16 @@ }, "bedrock/ap-northeast-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.45e-06, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.54e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -43989,13 +48474,18 @@ }, "bedrock/ap-south-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.41e-06, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", + "output_cost_per_token_batches": 7.1e-07, + "output_cost_per_token_flex": 7.1e-07, + "output_cost_per_token_priority": 2.47e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44008,7 +48498,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.236e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", @@ -44021,13 +48510,16 @@ }, "bedrock/eu-west-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.41e-06, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", + "output_cost_per_token_flex": 7.1e-07, + "output_cost_per_token_priority": 2.47e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44037,13 +48529,16 @@ }, "bedrock/eu-west-2/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 2.3e-07, + "input_cost_per_token_flex": 1.2e-07, + "input_cost_per_token_priority": 4e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.86e-06, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", + "output_cost_per_token_flex": 9.3e-07, + "output_cost_per_token_priority": 3.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44053,13 +48548,16 @@ }, "bedrock/sa-east-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.45e-06, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", + "output_cost_per_token_flex": 7.2e-07, + "output_cost_per_token_priority": 2.54e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44069,13 +48567,16 @@ }, "qwen.qwen3-vl-235b-a22b": { "input_cost_per_token": 5.3e-07, + "input_cost_per_token_batches": 2.6e-07, + "input_cost_per_token_priority": 9.3e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.66e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.33e-06, + "output_cost_per_token_priority": 4.66e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -44085,18 +48586,21 @@ }, "qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 8.75e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -44142,9 +48646,9 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, + "source": "https://replicate.com/meta/llama-2-13b", "supports_tool_choice": true }, "replicate/meta/llama-2-13b-chat": { @@ -44152,9 +48656,10 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, + "source": "https://replicate.com/meta/llama-2-13b-chat", + "supports_system_messages": true, "supports_tool_choice": true }, "replicate/meta/llama-2-70b": { @@ -44162,9 +48667,9 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.75e-06, + "source": "https://replicate.com/meta/llama-2-70b", "supports_tool_choice": true }, "replicate/meta/llama-2-70b-chat": { @@ -44172,9 +48677,10 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.75e-06, + "source": "https://replicate.com/meta/llama-2-70b-chat", + "supports_system_messages": true, "supports_tool_choice": true }, "replicate/meta/llama-2-7b": { @@ -44182,9 +48688,9 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/meta/llama-2-7b", "supports_tool_choice": true }, "replicate/meta/llama-2-7b-chat": { @@ -44192,9 +48698,10 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/meta/llama-2-7b-chat", + "supports_system_messages": true, "supports_tool_choice": true }, "replicate/meta/llama-3-70b": { @@ -44202,7 +48709,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.75e-06, "supports_tool_choice": true @@ -44212,7 +48718,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.75e-06, "supports_tool_choice": true @@ -44222,7 +48727,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8086, "max_output_tokens": 8086, - "max_tokens": 8086, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -44232,7 +48736,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8086, "max_output_tokens": 8086, - "max_tokens": 8086, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -44242,7 +48745,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -44252,9 +48754,9 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/mistralai/mistral-7b-v0.1", "supports_tool_choice": true }, "replicate/mistralai/mixtral-8x7b-instruct-v0.1": { @@ -44262,7 +48764,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06, "supports_tool_choice": true @@ -44272,8 +48773,10 @@ "output_cost_per_token": 1e-05, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-5", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -44284,6 +48787,7 @@ "output_cost_per_token": 3.6e-07, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-oss-20b", "supports_function_calling": true, "supports_system_messages": true }, @@ -44299,13 +48803,15 @@ "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://replicate.com/anthropic/claude-4.5-haiku" }, "replicate/ibm-granite/granite-3.3-8b-instruct": { "input_cost_per_token": 3e-08, "output_cost_per_token": 2.5e-07, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/ibm-granite/granite-3.3-8b-instruct", "supports_function_calling": true, "supports_system_messages": true }, @@ -44314,6 +48820,7 @@ "output_cost_per_token": 1e-05, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-4o", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, @@ -44355,6 +48862,7 @@ "output_cost_per_token": 6e-07, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-4o-mini", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, @@ -44367,6 +48875,7 @@ "output_cost_per_token": 1.06e-06, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/qwen/qwen3-235b-a22b-instruct-2507", "supports_function_calling": true, "supports_system_messages": true }, @@ -44391,7 +48900,7 @@ "mode": "chat", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, + "source": "https://replicate.com/deepseek-ai/deepseek-v3", "supports_function_calling": true, "supports_system_messages": true }, @@ -44447,7 +48956,9 @@ "supports_response_schema": false, "input_cost_per_token_above_200k_tokens": 4e-06, "output_cost_per_token_above_200k_tokens": 1.8e-05, + "source": "https://replicate.com/google/gemini-3-pro", "supports_audio_input": true, + "supports_reasoning": true, "supports_video_input": true }, "replicate/anthropic/claude-4.5-sonnet": { @@ -44462,13 +48973,15 @@ "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://replicate.com/anthropic/claude-4.5-sonnet" }, "replicate/openai/gpt-4.1": { "input_cost_per_token": 2e-06, "output_cost_per_token": 8e-06, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-4.1", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, @@ -44489,6 +49002,7 @@ "output_cost_per_token": 1.6e-06, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-4.1-mini", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, @@ -44501,16 +49015,21 @@ "output_cost_per_token": 4e-07, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-5-nano", "supports_function_calling": true, - "supports_system_messages": true + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true }, "replicate/openai/gpt-5-mini": { "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-5-mini", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -44521,6 +49040,7 @@ "output_cost_per_token": 2.5e-06, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/google/gemini-2.5-flash", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, @@ -44536,6 +49056,7 @@ "output_cost_per_token": 7.2e-07, "litellm_provider": "replicate", "mode": "chat", + "source": "https://replicate.com/openai/gpt-oss-120b", "supports_function_calling": true, "supports_system_messages": true }, @@ -44546,7 +49067,7 @@ "mode": "chat", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, + "source": "https://replicate.com/deepseek-ai/deepseek-v3.1", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true @@ -44567,7 +49088,7 @@ "mode": "chat", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, + "source": "https://replicate.com/deepseek-ai/deepseek-r1", "supports_reasoning": true, "supports_system_messages": true }, @@ -44577,7 +49098,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -44587,7 +49107,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -44597,7 +49116,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -44607,7 +49125,6 @@ "litellm_provider": "cohere", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cohere.com/pricing" @@ -44618,11 +49135,28 @@ "litellm_provider": "cohere", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cohere.com/pricing" }, + "rerank-v5.0-fast": { + "input_cost_per_token": 2e-08, + "litellm_provider": "cohere", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cohere.com/blog/rerank-5" + }, + "rerank-v5.0-pro": { + "input_cost_per_token": 5e-08, + "litellm_provider": "cohere", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cohere.com/blog/rerank-5" + }, "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3": { "input_cost_per_query": 0.0, "input_cost_per_token": 0.0, @@ -44649,7 +49183,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -44658,7 +49191,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -44667,7 +49199,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -44676,7 +49207,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -44685,7 +49215,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -44694,7 +49223,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -44703,7 +49231,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 196608, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://cloud.sambanova.ai/plans/pricing", @@ -44716,7 +49243,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7e-06, "source": "https://cloud.sambanova.ai/plans/pricing" @@ -44726,7 +49252,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" }, @@ -44743,7 +49268,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.sambanova.ai/plans/pricing", @@ -44752,7 +49276,6 @@ "supports_tool_choice": true }, "sambanova/DeepSeek-V3.1": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-06, @@ -44765,7 +49288,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.2e-07, @@ -44778,7 +49300,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/DeepSeek-V3.2": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 3e-06, @@ -44790,7 +49311,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/gemma-4-31B-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3.8e-07, @@ -44800,13 +49320,56 @@ "supports_vision": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, + "scx-ai/DeepSeek-V4.1-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "scx-ai", + "max_input_tokens": 1000000, + "max_output_tokens": 375000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://scx.ai/models/deepseek-v4-1-flash", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "scx-ai/GLM-5.3": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 9.8e-07, + "litellm_provider": "scx-ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.08e-06, + "source": "https://scx.ai/models/glm-5-3", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "scx-ai/Kimi-K3": { + "cache_read_input_token_cost": 2.8e-07, + "input_cost_per_token": 2.83e-06, + "litellm_provider": "scx-ai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.413e-05, + "source": "https://scx.ai/models/kimi-k3", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, "scx-ai/GLM-5.2": { "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 6.1e-07, "litellm_provider": "scx-ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.98e-06, "source": "https://scx.ai/pricing", @@ -44823,7 +49386,6 @@ "litellm_provider": "scx-ai", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.99e-06, "source": "https://scx.ai/pricing", @@ -44838,7 +49400,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 200000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, @@ -44854,7 +49415,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 1.35e-06, "output_cost_per_token": 5.4e-06, @@ -44865,56 +49425,48 @@ "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/jamba-1.5-large": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/jamba-1.5-mini": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/jamba-instruct": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama2-70b-chat": { "litellm_provider": "snowflake", "max_input_tokens": 4096, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3-70b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3-8b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3.1-405b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, @@ -44925,7 +49477,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 7.2e-07, "output_cost_per_token": 7.2e-07, @@ -44936,7 +49487,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 2.4e-07, "output_cost_per_token": 2.4e-07, @@ -44946,18 +49496,15 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3.2-3b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3.3-70b": { - "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 7.2e-07, @@ -44971,21 +49518,18 @@ "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/mistral-large": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/mistral-large2": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, @@ -44997,39 +49541,33 @@ "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/reka-core": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/reka-flash": { "litellm_provider": "snowflake", "max_input_tokens": 100000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-arctic": { "litellm_provider": "snowflake", "max_input_tokens": 4096, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-llama-3.1-405b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-llama-3.3-70b": { - "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 7.2e-07, @@ -45226,21 +49764,18 @@ "stability.sd3-5-large-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "stability.sd3-large-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "stability.stable-image-core-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, @@ -45250,96 +49785,184 @@ "mode": "image_edit", "output_cost_per_image": 0.4 }, + "us.stability.stable-conservative-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.4, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-creative-upscale-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.6 }, + "us.stability.stable-creative-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.6, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-fast-upscale-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.03 }, + "us.stability.stable-fast-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.03, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-outpaint-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.06 }, + "us.stability.stable-outpaint-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.06, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-control-sketch-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-control-sketch-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-control-structure-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-control-structure-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-erase-object-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-erase-object-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-inpaint-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-inpaint-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-remove-background-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-remove-background-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-search-recolor-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-search-recolor-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-search-replace-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-search-replace-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-style-guide-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-style-guide-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-style-transfer-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.08 }, + "us.stability.stable-style-transfer-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.08, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-core-v1:1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, "stability.stable-image-ultra-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.14 }, "stability.stable-image-ultra-v1:1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.14 }, @@ -45369,11 +49992,12 @@ "mode": "search" }, "text-completion-codestral/codestral-2405": { + "deprecation_date": "2025-06-16", + "deprecation_source": "https://docs.mistral.ai/getting-started/models/", "input_cost_per_token": 0.0, "litellm_provider": "text-completion-codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "completion", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/" @@ -45383,18 +50007,17 @@ "litellm_provider": "text-completion-codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "completion", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/" }, "text-embedding-004": { "deprecation_date": "2027-04-01", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -45402,11 +50025,11 @@ }, "text-embedding-005": { "deprecation_date": "2027-04-01", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -45417,7 +50040,6 @@ "input_cost_per_token_batches": 6.5e-08, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0, @@ -45429,7 +50051,6 @@ "input_cost_per_token_batches": 1e-08, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0, @@ -45440,7 +50061,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -45451,7 +50071,6 @@ "input_cost_per_token_batches": 5e-08, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0 @@ -45461,7 +50080,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -45471,7 +50089,6 @@ "input_cost_per_token": 6.25e-09, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 3072, - "max_tokens": 3072, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -45479,11 +50096,11 @@ }, "text-multilingual-embedding-002": { "deprecation_date": "2027-04-01", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -45494,7 +50111,6 @@ "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "completion", "output_cost_per_token": 2.8e-05, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -45504,7 +50120,6 @@ "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "completion", "output_cost_per_token": 2.8e-05, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -45530,7 +50145,8 @@ "together-ai-8.1b-21b": { "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", - "max_tokens": 1000, + "max_output_tokens": 1000, + "max_input_tokens": 1000, "mode": "chat", "output_cost_per_token": 3e-07 }, @@ -45583,7 +50199,6 @@ "litellm_provider": "together_ai", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "metadata": { "successor": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" }, @@ -45595,13 +50210,16 @@ "supports_tool_choice": true }, "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "deprecation_date": "2026-10-22", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.04e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.04e-06, "source": "https://api.together.ai/v1/models", + "successor_model": "together_ai/meta-models/Muse-Glimmer-30B", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -45625,7 +50243,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.together.ai/v1/models", @@ -45646,7 +50264,7 @@ "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 202752, - "max_tokens": 202752, + "max_output_tokens": 202752, "metadata": { "successor": "together_ai/zai-org/GLM-5.2" }, @@ -45660,13 +50278,16 @@ }, "together_ai/MiniMaxAI/MiniMax-M3": { "cache_read_input_token_cost": 6e-08, + "deprecation_date": "2026-11-06", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 524288, - "max_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", + "successor_model": "together_ai/MiniMaxAI/MiniMax-M3.1-Flash", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -45675,11 +50296,22 @@ "supports_tool_choice": true, "supports_vision": true }, + "together_ai/MiniMaxAI/MiniMax-M3.1-Flash": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://www.together.ai/pricing", + "supports_prompt_caching": true + }, "together_ai/Prism-ML/Ternary-Bonsai-27B": { "input_cost_per_token": 0.0, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.together.ai/docs/serverless-models" @@ -45688,7 +50320,7 @@ "input_cost_per_token": 1.7e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://api.together.ai/v1/models", @@ -45703,7 +50335,7 @@ "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://api.together.ai/v1/models", @@ -45714,50 +50346,56 @@ "input_cost_per_token": 2.5e-06, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 7.5e-06, - "source": "https://api.together.ai/v1/models", + "source": "https://www.together.ai/pricing", "supports_prompt_caching": true }, "together_ai/Qwen/Qwen3.7-Plus": { "input_cost_per_token": 3.2e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.28e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3.8-2.4T-A95B": { "cache_read_input_token_cost": 2.5e-07, + "deprecation_date": "2026-11-04", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 1010000, - "max_tokens": 1010000, + "max_output_tokens": 1010000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://api.together.ai/v1/models", + "successor_model": "together_ai/Qwen/Qwen3.7-Max", "supports_prompt_caching": true }, "together_ai/arize-ai/qwen-2-1.5b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2026-10-22", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.4e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://api.together.ai/v1/models", + "successor_model": "together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -45769,7 +50407,7 @@ "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", @@ -45783,7 +50421,7 @@ "input_cost_per_token": 1.32e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://api.together.ai/v1/models", @@ -45793,25 +50431,41 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "together_ai/deepseek-pro-latest": { + "alias_of": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" + }, "together_ai/meta-models/Muse-Glimmer-30B": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 3.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, + "together_ai/meta-models/Muse-Spark-Open-816B-A42B": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "source": "https://docs.together.ai/docs/serverless-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, "together_ai/moonshotai/Kimi-K3": { - "cache_read_input_token_cost": 2.7e-07, - "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 1.35e-05, + "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ "low", "high", @@ -45826,15 +50480,21 @@ "supports_tool_choice": true, "supports_vision": true }, + "together_ai/kimi-latest": { + "alias_of": "together_ai/moonshotai/Kimi-K3" + }, "together_ai/thinkingmachines/Inkling": { "cache_read_input_token_cost": 1.7e-07, + "deprecation_date": "2026-11-06", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "max_input_tokens": 524288, - "max_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 4.05e-06, "source": "https://api.together.ai/v1/models", + "successor_model": "together_ai/meta-models/Muse-Spark-Open-816B-A42B", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -45847,7 +50507,6 @@ "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.together.ai/v1/models", @@ -45864,7 +50523,6 @@ "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.together.ai/v1/models", @@ -45875,13 +50533,15 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "together_ai/glm-latest": { + "alias_of": "together_ai/zai-org/GLM-5.3" + }, "together_ai/zai-org/GLM-5.3-Flash": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://api.together.ai/v1/models", @@ -45893,8 +50553,13 @@ "supports_tool_choice": true, "supports_vision": true }, + "together_ai/glm-flash-latest": { + "alias_of": "together_ai/zai-org/GLM-5.3-Flash" + }, "tts-1": { "deprecation_date": "2027-01-06", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_character": 1.5e-05, "litellm_provider": "openai", "mode": "audio_speech", @@ -45905,6 +50570,8 @@ }, "tts-1-hd": { "deprecation_date": "2027-01-06", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_character": 3e-05, "litellm_provider": "openai", "mode": "audio_speech", @@ -45962,12 +50629,14 @@ "us.amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, + "output_cost_per_token_batches": 1.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -45978,12 +50647,14 @@ "us.amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 8.75e-09, "input_cost_per_token": 3.5e-08, + "input_cost_per_token_batches": 1.75e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, + "output_cost_per_token_batches": 7e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, @@ -45992,15 +50663,20 @@ "us.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 8e-07, + "input_cost_per_token_batches": 4e-07, "input_cost_per_token_flex": 4e-07, + "input_cost_per_token_priority": 1.4e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, + "output_cost_per_token_batches": 1.6e-06, "output_cost_per_token_flex": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -46015,7 +50691,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -46035,7 +50710,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -46052,14 +50726,17 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -46077,7 +50754,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -46096,7 +50772,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -46114,7 +50789,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -46128,11 +50802,11 @@ "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2027-01-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -46150,7 +50824,11 @@ "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-1-20250805-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, @@ -46163,11 +50841,12 @@ "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "deprecation_date": "2027-04-08", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "us.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -46189,7 +50868,11 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -46201,11 +50884,13 @@ "cache_creation_input_token_cost_above_200k_tokens": 9e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.44e-05, "cache_read_input_token_cost_above_200k_tokens": 7.2e-07, + "deprecation_date": "2027-04-27", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "us-gov.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -46220,7 +50905,11 @@ "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "us-gov.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -46233,18 +50922,19 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -46254,7 +50944,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -46267,7 +50962,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, @@ -46279,6 +50973,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -46288,7 +50983,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -46300,12 +51000,12 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json", "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -46321,7 +51021,14 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + }, + "input_cost_per_token_batches": 3e-06, + "output_cost_per_token_batches": 1.5e-05 }, "us-gov.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -46333,7 +51040,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.4e-05, "prompt_cache_min_tokens": 512, @@ -46345,6 +51051,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -46356,7 +51063,12 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.5e-05, @@ -46366,7 +51078,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, @@ -46385,19 +51096,24 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-fable-5-1", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -46411,11 +51127,11 @@ }, "us-gov.nvidia.nemotron-nano-12b-v2": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "input_cost_per_token": 2.4e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", @@ -46427,11 +51143,11 @@ }, "us-gov.nvidia.nemotron-nano-9b-v2": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "input_cost_per_token": 7.2e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", @@ -46446,7 +51162,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -46459,11 +51174,11 @@ "supports_vision": false }, "us-gov.openai.gpt-oss-20b-1:0": { + "supports_vision": false, "input_cost_per_token": 8.4e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", @@ -46478,11 +51193,11 @@ "supports_tool_choice": true }, "us-gov.openai.gpt-oss-120b-1:0": { + "supports_vision": false, "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", @@ -46509,7 +51224,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": false, @@ -46526,7 +51240,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "supports_assistant_prefill": true, @@ -46543,7 +51256,11 @@ "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, "output_cost_per_token_batches": 2.75e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -46552,7 +51269,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -46580,7 +51296,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -46602,7 +51317,11 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -46613,7 +51332,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -46635,7 +51353,11 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.875e-06, @@ -46646,7 +51368,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -46668,21 +51389,26 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "us.anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -46701,15 +51427,19 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "us.deepseek.r1-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", "input_cost_per_token": 1.35e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", @@ -46719,14 +51449,18 @@ }, "us.deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_batches": 3.1e-07, "input_cost_per_token_flex": 3.1e-07, + "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_batches": 9.25e-07, "output_cost_per_token_flex": 9.25e-07, + "output_cost_per_token_priority": 3.2375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -46741,7 +51475,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 2.22e-06, "output_cost_per_token_flex": 1.11e-06, @@ -46754,11 +51487,12 @@ "supports_vision": false }, "us.meta.llama3-1-405b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -46767,36 +51501,41 @@ }, "us.meta.llama3-1-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-1-70b-instruct.md", + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-1-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.2e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-1-8b-instruct.md", + "output_cost_per_token_batches": 1.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-2-11b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.6e-07, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -46805,33 +51544,38 @@ "supports_vision": true }, "us.meta.llama3-2-1b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-2-3b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-2-90b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -46841,25 +51585,27 @@ }, "us.meta.llama3-3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-3-70b-instruct.md", + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama4-maverick-17b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md", "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9.7e-07, "output_cost_per_token_batches": 4.85e-07, @@ -46877,12 +51623,12 @@ }, "us.meta.llama4-scout-17b-instruct-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md", "input_cost_per_token": 1.7e-07, "input_cost_per_token_batches": 8.5e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 10000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_batches": 3.3e-07, @@ -46903,7 +51649,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.md", @@ -46915,7 +51660,6 @@ "litellm_provider": "v0", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -46929,7 +51673,6 @@ "litellm_provider": "v0", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -46943,7 +51686,6 @@ "litellm_provider": "v0", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -46957,7 +51699,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.4e-07 }, @@ -46966,7 +51707,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07 }, @@ -46975,7 +51715,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07 }, @@ -46984,7 +51723,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -46995,7 +51733,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 262144, "max_output_tokens": 66536, - "max_tokens": 66536, "mode": "chat", "output_cost_per_token": 1.6e-06, "supports_function_calling": true, @@ -47006,7 +51743,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 300000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-07, "supports_vision": true, @@ -47018,7 +51754,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.4e-07, "supports_function_calling": true, @@ -47029,7 +51764,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 300000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.2e-06, "supports_vision": true, @@ -47041,7 +51775,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -47052,7 +51785,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_vision": true, @@ -47067,7 +51799,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_vision": true, @@ -47082,7 +51813,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_vision": true, @@ -47097,7 +51827,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -47112,7 +51841,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -47127,7 +51855,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_vision": true, @@ -47142,7 +51869,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -47155,7 +51881,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -47173,7 +51898,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -47191,7 +51915,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -47210,7 +51933,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -47230,7 +51952,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, @@ -47250,7 +51971,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, @@ -47270,7 +51990,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": true, @@ -47293,10 +52012,9 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -47314,7 +52032,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -47334,7 +52051,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -47351,7 +52067,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -47363,7 +52078,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -47374,7 +52088,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -47385,7 +52098,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -47394,7 +52106,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.19e-06, "supports_tool_choice": true @@ -47404,7 +52115,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 9.9e-07, "supports_function_calling": true, @@ -47416,7 +52126,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "supports_tool_choice": true @@ -47426,7 +52135,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1000000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.5e-06, "supports_vision": true, @@ -47445,7 +52153,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, @@ -47466,7 +52173,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -47475,7 +52181,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "supports_vision": true, @@ -47487,7 +52192,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -47496,7 +52200,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -47505,7 +52208,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -47514,7 +52216,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.9e-07, "supports_tool_choice": true @@ -47524,7 +52225,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 8e-08, "supports_tool_choice": true @@ -47534,7 +52234,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_tool_choice": true @@ -47544,7 +52243,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-08, "supports_function_calling": true, @@ -47555,7 +52253,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.6e-07, "supports_vision": true, @@ -47567,7 +52264,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-07 }, @@ -47576,7 +52272,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_function_calling": true, @@ -47587,7 +52282,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_vision": true, @@ -47599,7 +52293,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_function_calling": true, @@ -47610,7 +52303,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "supports_tool_choice": true @@ -47620,7 +52312,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-07, "supports_vision": true, @@ -47632,7 +52323,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 9e-07, "supports_function_calling": true, @@ -47643,7 +52333,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -47652,7 +52341,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.8e-07, "supports_function_calling": true, @@ -47664,7 +52352,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_function_calling": true, @@ -47676,7 +52363,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true @@ -47686,7 +52372,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-08, "supports_function_calling": true, @@ -47697,7 +52382,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1e-07, "supports_vision": true, @@ -47709,7 +52393,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -47718,7 +52401,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -47729,7 +52411,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.9e-07 }, @@ -47738,7 +52419,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -47750,7 +52430,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 65536, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true @@ -47760,7 +52439,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_vision": true, @@ -47773,7 +52451,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_vision": true, @@ -47786,7 +52463,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.2e-06, "supports_function_calling": true, @@ -47797,7 +52473,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, @@ -47806,7 +52481,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.9e-06 }, @@ -47815,7 +52489,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -47826,7 +52499,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06 }, @@ -47835,7 +52507,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_vision": true, @@ -47849,7 +52520,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "supports_vision": true, @@ -47864,7 +52534,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "supports_vision": true, @@ -47879,7 +52548,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_vision": true, @@ -47894,7 +52562,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, @@ -47909,7 +52576,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "supports_vision": true, @@ -47924,7 +52590,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_vision": true, @@ -47939,7 +52604,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_vision": true, @@ -47954,7 +52618,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, @@ -47968,7 +52631,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_vision": true, @@ -47981,7 +52643,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -47990,7 +52651,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -47999,7 +52659,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -48008,7 +52667,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -48017,7 +52675,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-05 }, @@ -48026,7 +52683,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 5e-06 }, @@ -48035,7 +52691,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8e-06 }, @@ -48044,7 +52699,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -48056,7 +52710,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -48068,7 +52721,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -48079,7 +52731,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, @@ -48091,7 +52742,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -48102,7 +52752,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_function_calling": true @@ -48112,7 +52761,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "supports_function_calling": true, @@ -48123,7 +52771,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "supports_function_calling": true, @@ -48134,7 +52781,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -48145,7 +52791,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-06, "supports_function_calling": true, @@ -48156,7 +52801,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 96000, - "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 1.1e-06, "supports_function_calling": true, @@ -48168,7 +52812,6 @@ "input_cost_per_token": 4.5e-07, "max_input_tokens": 200000, "max_output_tokens": 200000, - "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 1.8e-06, "source": "https://vercel.com/ai-gateway/models/glm-4.6", @@ -48219,7 +52862,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -48233,7 +52875,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -48243,6 +52884,7 @@ }, "vertex_ai/claude-haiku-4-5": { "deprecation_date": "2026-10-15", + "successor_model": "vertex_ai/claude-haiku-5-5", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_creation_input_token_cost_batches": 6.25e-07, @@ -48253,8 +52895,12 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, "regional_endpoint_uplift_multiplier": 1.1, @@ -48282,8 +52928,12 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, "regional_endpoint_uplift_multiplier": 1.1, @@ -48305,7 +52955,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -48321,7 +52970,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -48336,7 +52984,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_assistant_prefill": true, @@ -48350,7 +52997,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_assistant_prefill": true, @@ -48358,40 +53004,11 @@ "supports_tool_choice": true, "supports_vision": true }, - "vertex_ai/claude-3-opus": { - "deprecation_date": "2025-08-01", - "input_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "vertex_ai/claude-3-opus@20240229": { - "deprecation_date": "2025-08-01", - "input_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, "vertex_ai/claude-3-sonnet": { "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -48404,7 +53021,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -48414,6 +53030,7 @@ }, "vertex_ai/claude-opus-4-5": { "deprecation_date": "2026-11-24", + "successor_model": "vertex_ai/claude-opus-5-5", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, @@ -48424,7 +53041,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -48459,7 +53075,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -48498,7 +53113,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -48536,7 +53150,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -48573,7 +53186,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -48611,7 +53223,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -48649,7 +53260,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -48687,7 +53297,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -48717,6 +53326,91 @@ "output_cost_per_token_batches": 2.5e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, + "vertex_ai/claude-fable-5-2": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-11-09", + "input_cost_per_token_batches": 4e-06, + "output_cost_per_token_batches": 2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-mythos-5-2": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-11-09", + "input_cost_per_token_batches": 4e-06, + "output_cost_per_token_batches": 2e-05, + "source": "https://platform.claude.com/docs/en/models/mythos-5-2/overview" + }, + "vertex_ai/claude-fable-latest": { + "alias_of": "vertex_ai/claude-fable-5-2" + }, "vertex_ai/claude-fable-5@default": { "deprecation_date": "2027-06-08", "regional_endpoint_uplift_multiplier": 1.1, @@ -48731,7 +53425,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -48769,7 +53462,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -48799,11 +53491,94 @@ "output_cost_per_token_batches": 2.5e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, + "vertex_ai/claude-fable-5-2@default": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-11-09", + "input_cost_per_token_batches": 4e-06, + "output_cost_per_token_batches": 2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-mythos-5-2@default": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-11-09", + "input_cost_per_token_batches": 4e-06, + "output_cost_per_token_batches": 2e-05, + "source": "https://platform.claude.com/docs/en/models/mythos-5-2/overview" + }, "vertex_ai/claude-opus-5": { "deprecation_date": "2027-01-24", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, @@ -48814,7 +53589,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -48843,6 +53617,7 @@ "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, @@ -48853,7 +53628,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -48890,7 +53664,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1.25e-05, @@ -48918,6 +53691,9 @@ "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, + "vertex_ai/claude-opus-latest": { + "alias_of": "vertex_ai/claude-opus-5-5" + }, "vertex_ai/claude-opus-5-5@default": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, @@ -48931,7 +53707,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1.25e-05, @@ -48974,7 +53749,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -49013,7 +53787,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -49039,6 +53812,7 @@ }, "vertex_ai/claude-sonnet-4-5": { "deprecation_date": "2026-09-29", + "successor_model": "vertex_ai/claude-sonnet-5-5", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, @@ -49053,8 +53827,12 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "regional_endpoint_uplift_multiplier": 1.1, @@ -49083,7 +53861,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -49093,6 +53870,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -49122,11 +53900,10 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -49161,8 +53938,12 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "regional_endpoint_uplift_multiplier": 1.1, @@ -49185,7 +53966,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -49197,7 +53977,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -49209,7 +53988,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -49221,7 +53999,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -49233,7 +54010,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -49244,7 +54020,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -49255,7 +54030,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -49269,7 +54043,6 @@ "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.7e-06, "output_cost_per_token_batches": 8.5e-07, @@ -49291,7 +54064,6 @@ "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.68e-06, "output_cost_per_token_batches": 8.4e-07, @@ -49299,8 +54071,9 @@ "supported_regions": [ "global" ], - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -49312,7 +54085,6 @@ "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 65336, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "output_cost_per_token_batches": 2.7e-06, @@ -49320,14 +54092,17 @@ "supported_regions": [ "us-central1" ], - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "vertex_ai/gemini-2.5-flash-image": { "deprecation_date": "2027-03-15", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/gemini-3.1-flash-lite-image", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, @@ -49335,10 +54110,10 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, @@ -49383,7 +54158,6 @@ "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.6e-07, - "deprecation_date": "2027-05-28", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, @@ -49394,25 +54168,25 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, + "output_cost_per_image_token_batches": 6e-05, + "output_cost_per_image_token_priority": 0.000216, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, - "supports_reasoning": false, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" - ] - + ], + "supports_reasoning": false }, "vertex_ai/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -49429,17 +54203,18 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, + "output_cost_per_image_token_batches": 6e-05, + "output_cost_per_image_token_priority": 0.000216, "output_cost_per_token": 1.2e-05, "output_cost_per_token_priority": 2.16e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "supports_reasoning": false, - "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", @@ -49453,33 +54228,32 @@ "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, "cache_read_input_token_cost_priority": 9e-08, - "deprecation_date": "2027-05-28", "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 65536, + "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, + "output_cost_per_image_token_batches": 3e-05, + "output_cost_per_image_token_priority": 0.000108, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.4e-06, "regional_endpoint_uplift_multiplier": 1.1, - "supports_reasoning": false, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" - ] - + ], + "supports_reasoning": false }, "vertex_ai/gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, @@ -49490,14 +54264,15 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, + "output_cost_per_image_token_batches": 3e-05, + "output_cost_per_image_token_priority": 0.000108, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "supports_reasoning": false, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", @@ -49511,7 +54286,6 @@ "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, - "deprecation_date": "2027-06-28", "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, @@ -49520,10 +54294,11 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, + "output_cost_per_image_token_priority": 5.4e-05, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, @@ -49560,7 +54335,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, @@ -49599,26 +54373,35 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3.1-flash-lite": { "cache_read_input_audio_token_cost": 5e-08, - "deprecation_date": "2027-05-07", + "cache_read_input_audio_token_cost_batches": 2.5e-08, + "cache_read_input_audio_token_cost_flex": 2.5e-08, + "cache_read_input_audio_token_cost_priority": 9e-08, "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 5e-07, + "input_cost_per_audio_token_above_200k_tokens": 5e-07, + "input_cost_per_audio_token_above_200k_tokens_batches": 2.5e-07, + "input_cost_per_audio_token_above_200k_tokens_flex": 2.5e-07, + "input_cost_per_audio_token_above_200k_tokens_priority": 9e-07, + "input_cost_per_audio_token_batches": 2.5e-07, + "input_cost_per_audio_token_flex": 2.5e-07, + "input_cost_per_audio_token_priority": 9e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, - "input_cost_per_audio_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, @@ -49626,7 +54409,10 @@ "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "vertex_ai/gemini-3.5-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -49644,6 +54430,7 @@ "supports_audio_input": true, "supports_audio_output": false, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -49655,22 +54442,14 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.5-flash-lite": { - "deprecation_date": "2027-07-21", "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_batches": 1.5e-08, "cache_read_input_token_cost_flex": 1.5e-08, "cache_read_input_token_cost_priority": 5.4e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, @@ -49678,7 +54457,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -49686,6 +54464,8 @@ "output_cost_per_token_flex": 1.25e-06, "output_cost_per_token_priority": 4.5e-06, "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -49703,26 +54483,22 @@ ], "supports_audio_input": true, "supports_audio_output": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "web_search_billing_unit": "per_query" }, "vertex_ai/deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, @@ -49733,7 +54509,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -49747,7 +54522,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -49758,7 +54532,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -49769,7 +54542,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -49780,7 +54552,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -49791,7 +54562,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -49821,7 +54591,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "audio_speech", "output_cost_per_image": 0.04, "output_cost_per_token": 0, @@ -49857,7 +54626,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "audio_speech", "output_cost_per_image": 0.08, "output_cost_per_token": 0, @@ -49894,7 +54662,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.6e-05, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", @@ -49907,7 +54674,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", @@ -49920,7 +54686,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." }, @@ -49936,7 +54701,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." }, @@ -49953,7 +54717,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.15e-06, "output_cost_per_token_batches": 5.75e-07, @@ -49971,12 +54734,13 @@ }, "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": { "input_cost_per_token": 3.5e-07, + "input_cost_per_token_batches": 1.75e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.15e-06, + "output_cost_per_token_batches": 5.75e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", @@ -49991,12 +54755,13 @@ }, "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": { "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, - "max_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-07, + "output_cost_per_token_batches": 3.5e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", @@ -50015,7 +54780,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, - "max_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-07, "output_cost_per_token_batches": 3.5e-07, @@ -50036,7 +54800,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", @@ -50047,7 +54810,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", @@ -50058,7 +54820,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", @@ -50071,7 +54832,6 @@ "litellm_provider": "vertex_ai-minimax_models", "max_input_tokens": 196608, "max_output_tokens": 196608, - "max_tokens": 196608, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50085,22 +54845,22 @@ "litellm_provider": "vertex_ai-moonshot_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_web_search": true }, "vertex_ai/zai-org/glm-4.7-maas": { "cache_read_input_token_cost": 6e-08, "deprecation_date": "2026-10-21", + "successor_model": "vertex_ai/zai-org/glm-5.2-maas", "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50108,17 +54868,18 @@ "global" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true }, "vertex_ai/zai-org/glm-5-maas": { "cache_read_input_token_cost": 1e-07, "deprecation_date": "2026-10-21", + "successor_model": "vertex_ai/zai-org/glm-5.2-maas", "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50126,6 +54887,7 @@ "global" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -50135,7 +54897,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50147,7 +54908,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50159,7 +54919,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50171,7 +54930,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50183,7 +54941,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -50194,7 +54951,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -50205,7 +54961,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -50216,7 +54971,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -50227,7 +54981,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, @@ -50238,7 +54991,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_function_calling": true, @@ -50249,7 +55001,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -50262,7 +55013,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -50296,7 +55046,6 @@ "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 262144, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/maas/google/gemma-4-26b-a4b-it", @@ -50313,11 +55062,11 @@ "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.6e-07, "output_cost_per_token_batches": 1.8e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supports_pdf_input": false, "supports_reasoning": true }, "vertex_ai/openai/gpt-oss-20b-maas": { @@ -50326,10 +55075,10 @@ "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supports_pdf_input": false, "supports_reasoning": true, "cache_read_input_token_cost": 7e-09, "input_cost_per_token_batches": 3.5e-08, @@ -50341,7 +55090,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50358,7 +55106,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50378,7 +55125,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, - "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -50398,7 +55144,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, - "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -50419,7 +55164,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 200000, "max_output_tokens": 200000, - "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -50439,7 +55183,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 524288, "max_output_tokens": 524288, - "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, @@ -50458,7 +55201,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 8.8e-07, "output_cost_per_token_batches": 4.4e-07, @@ -50468,6 +55210,7 @@ "us-south1" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { @@ -50478,7 +55221,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-06, "output_cost_per_token_batches": 9e-07, @@ -50487,6 +55229,7 @@ "global" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas": { @@ -50495,7 +55238,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50503,6 +55245,7 @@ "global" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas": { @@ -50511,7 +55254,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -50519,12 +55261,12 @@ "global" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true }, "vertex_ai/veo-3.1-generate-preview": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, @@ -50539,7 +55281,6 @@ "vertex_ai/veo-3.1-fast-generate-preview": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -50553,14 +55294,13 @@ ] }, "vertex_ai/veo-3.1-generate-001": { - "deprecation_date": "2026-11-17", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "successor_model": "vertex_ai/gemini-omni-1.2-flash", "supported_modalities": [ "text" ], @@ -50569,15 +55309,14 @@ ] }, "vertex_ai/veo-3.1-fast-generate-001": { - "deprecation_date": "2026-11-17", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, "output_cost_per_second_4k": 0.3, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "successor_model": "vertex_ai/gemini-omni-1.2-flash", "supported_modalities": [ "text" ], @@ -50588,7 +55327,6 @@ "vertex_ai/veo-3.1-lite-generate-001": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.08, @@ -50606,7 +55344,6 @@ "litellm_provider": "voyage", "max_input_tokens": 16000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -50615,7 +55352,6 @@ "litellm_provider": "voyage", "max_input_tokens": 8000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -50624,7 +55360,6 @@ "litellm_provider": "voyage", "max_input_tokens": 8000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.voyageai.com/docs/pricing" @@ -50634,7 +55369,6 @@ "litellm_provider": "voyage", "max_input_tokens": 4000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.voyageai.com/docs/pricing" @@ -50644,7 +55378,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -50653,7 +55386,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -50662,7 +55394,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.voyageai.com/docs/pricing" @@ -50672,7 +55403,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.voyageai.com/docs/pricing" @@ -50681,7 +55411,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4000, - "max_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50689,7 +55418,6 @@ "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50697,7 +55425,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -50707,7 +55434,6 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50715,7 +55441,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50723,7 +55448,6 @@ "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50731,7 +55455,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50739,7 +55462,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 16000, - "max_tokens": 16000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50747,7 +55469,6 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50755,7 +55476,6 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 120000, - "max_tokens": 120000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50763,7 +55483,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50771,7 +55490,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 16000, - "max_tokens": 16000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50779,7 +55497,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 16000, - "max_tokens": 16000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -50789,15 +55506,13 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 16000, - "max_tokens": 16000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-lite-01": { "input_cost_per_token": 1e-07, "litellm_provider": "voyage", - "max_input_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50805,7 +55520,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4000, - "max_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50813,13 +55527,12 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "supports_embedding_image_input": true }, "wandb/openai/gpt-oss-120b": { "supports_reasoning": true, - "max_tokens": 131072, "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -50830,7 +55543,6 @@ }, "wandb/openai/gpt-oss-20b": { "supports_reasoning": true, - "max_tokens": 131072, "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -50840,7 +55552,6 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/moonshotai/Kimi-K2.5": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "cache_read_input_token_cost": 1e-07, @@ -50855,28 +55566,27 @@ "supports_vision": true }, "wandb/meta-llama/Llama-3.1-8B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 131000, + "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2.2e-07, "output_cost_per_token": 2.2e-07, "litellm_provider": "wandb", "mode": "chat", - "source": "https://wandb.ai/site/pricing/tokens/" + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "wandb/deepseek-ai/DeepSeek-V3.1": { + "cache_read_input_token_cost": 2e-07, "supports_reasoning": true, - "max_tokens": 128000, - "max_input_tokens": 161000, + "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 5.5e-07, - "output_cost_per_token": 1.65e-06, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, "litellm_provider": "wandb", "mode": "chat", - "source": "https://wandb.ai/site/pricing/tokens/" + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", + "supports_prompt_caching": true }, "wandb/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 7.1e-07, @@ -50890,7 +55600,6 @@ "litellm_provider": "watsonx", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 2e-07, "supports_audio_input": false, @@ -50908,7 +55617,6 @@ "litellm_provider": "watsonx", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_audio_input": false, @@ -50922,7 +55630,6 @@ "supports_vision": false }, "watsonx/bigscience/mt0-xxl-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.908e-06, @@ -50935,7 +55642,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/bigscience/mt0-xxl": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.908e-06, @@ -50948,11 +55654,10 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/core42/jais-13b-chat": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 0.0005, - "output_cost_per_token": 0.002, + "input_cost_per_token": 1.8e-06, + "output_cost_per_token": 1.8e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, @@ -50960,7 +55665,6 @@ "supports_vision": false }, "watsonx/google/flan-t5-xl-3b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, @@ -50972,7 +55676,6 @@ "supports_vision": false }, "watsonx/ibm/granite-13b-chat-v2": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, @@ -50984,7 +55687,6 @@ "supports_vision": false }, "watsonx/ibm/granite-13b-instruct-v2": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, @@ -50996,7 +55698,6 @@ "supports_vision": false }, "watsonx/ibm/granite-3-3-8b-instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -51008,7 +55709,6 @@ "supports_vision": false }, "watsonx/ibm/granite-4-h-small": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6.36e-08, @@ -51021,7 +55721,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/ibm/granite-guardian-3-2-2b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -51033,7 +55732,6 @@ "supports_vision": false }, "watsonx/ibm/granite-guardian-3-3-8b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -51045,7 +55743,6 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-1024-96-r2": { - "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, @@ -51057,7 +55754,6 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-1536-96-r2": { - "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, @@ -51069,7 +55765,6 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-512-96-r2": { - "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, @@ -51081,7 +55776,6 @@ "supports_vision": false }, "watsonx/ibm/granite-vision-3-2-2b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -51093,7 +55787,6 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-2-11b-vision-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, @@ -51105,7 +55798,6 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-2-1b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1e-07, @@ -51117,7 +55809,6 @@ "supports_vision": false }, "watsonx/meta-llama/llama-3-2-3b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.5e-07, @@ -51129,7 +55820,6 @@ "supports_vision": false }, "watsonx/meta-llama/llama-3-2-90b-vision-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-06, @@ -51141,7 +55831,6 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-3-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 7.526e-07, @@ -51154,7 +55843,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3.71e-07, @@ -51167,7 +55855,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3.71e-07, @@ -51180,7 +55867,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-guard-3-11b-vision": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, @@ -51192,7 +55878,6 @@ "supports_vision": true }, "watsonx/mistralai/mistral-medium-2505": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3e-06, @@ -51204,7 +55889,6 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-2503": { - "max_tokens": 32000, "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 1e-07, @@ -51216,7 +55900,6 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { - "max_tokens": 16384, "max_input_tokens": 131072, "max_output_tokens": 16384, "input_cost_per_token": 1.06e-07, @@ -51229,7 +55912,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/mistralai/pixtral-12b-2409": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, @@ -51241,7 +55923,6 @@ "supports_vision": true }, "watsonx/openai/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.59e-07, @@ -51254,7 +55935,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/sdaia/allam-1-13b-instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1.8e-06, @@ -51283,6 +55963,8 @@ "/v1/audio/transcriptions" ], "deprecation_date": "2027-02-26", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-live-transcribe", "source": "https://developers.openai.com/api/docs/pricing" }, "xai/grok-4.20-multi-agent-beta-0309": { @@ -51291,7 +55973,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -51316,7 +55997,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -51340,7 +56020,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -51366,7 +56045,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -51392,9 +56070,10 @@ "input_cost_per_token_above_200k_tokens_batches": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", + "token_count_framing": 185, + "token_count_tool_framing": 214, "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -51422,7 +56101,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -51446,7 +56124,6 @@ "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, @@ -51468,7 +56145,6 @@ "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, @@ -51490,7 +56166,6 @@ "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, @@ -51512,7 +56187,6 @@ "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, @@ -51528,16 +56202,21 @@ "xai/grok-4.7": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "cache_read_input_token_cost_above_200k_tokens_batches": 8e-07, + "cache_read_input_token_cost_batches": 4e-07, "input_cost_per_image_token": 2e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_batches": 3.2e-06, + "input_cost_per_token_batches": 1.6e-06, "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, + "output_cost_per_token_above_200k_tokens_batches": 9.6e-06, + "output_cost_per_token_batches": 4.8e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, @@ -51547,60 +56226,77 @@ "supports_vision": true, "supports_web_search": true }, + "xai/grok-latest": { + "alias_of": "xai/grok-4.7" + }, "zai.glm-4.7": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "zai.glm-5", "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 203000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_flex": 1.1e-06, + "output_cost_per_token_priority": 3.85e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-zai-glm-4-7.md", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "zai.glm-5": { "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "input_cost_per_token_flex": 5e-07, + "input_cost_per_token_priority": 1.75e-06, "output_cost_per_token": 3.2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 1.6e-06, + "output_cost_per_token_flex": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "zai.glm-4.7-flash": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3.5e-08, "input_cost_per_token_flex": 3.5e-08, + "input_cost_per_token_priority": 1.225e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 203000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, "output_cost_per_token_flex": 2e-07, + "output_cost_per_token_priority": 7e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-zai-glm-4-7-flash.md", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -51633,8 +56329,12 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true }, + "zai/glm-latest": { + "alias_of": "zai/glm-5.3" + }, "zai/glm-5.3-flash": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 3e-08, @@ -51647,10 +56347,29 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "supports_vision": true }, + "zai/glm-flash-latest": { + "alias_of": "zai/glm-5.3-flash" + }, + "zai/glm-5v-turbo": { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "litellm_provider": "zai", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://vercel.com/ai-gateway/models/glm-5v-turbo", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, "zai/glm-5.1": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2.6e-07, @@ -51880,6 +56599,7 @@ }, "openai/sora-2": { "deprecation_date": "2026-09-24", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, @@ -51894,6 +56614,7 @@ }, "openai/sora-2-pro": { "deprecation_date": "2026-09-24", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.3, @@ -51909,6 +56630,7 @@ "openai/sora-2-pro-high-res": { "litellm_provider": "openai", "deprecation_date": "2026-09-24", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "mode": "video_generation", "output_cost_per_video_per_second": 0.5, "source": "https://platform.openai.com/docs/api-reference/videos", @@ -52008,7 +56730,7 @@ "runwayml/seedance2": { "litellm_provider": "runwayml", "mode": "video_generation", - "output_cost_per_second": 0.36, + "output_cost_per_second": 0.3, "output_cost_per_second_1080p": 0.4, "output_cost_per_second_4k": 1.5, "source": "https://docs.dev.runwayml.com/guides/pricing/", @@ -52020,14 +56742,13 @@ "supported_output_modalities": [ "video" ], - "metadata": { - "comment": "36 credits per second at 480p/720p, 40 at 1080p, 150 at 4K @ $0.01 per credit" - } + "metadata": {"comment":"14/30/40/150 credits per second at 480p/720p/1080p/4K @ $0.01 per credit; 56 credit minimum per generation not modeled"}, + "output_cost_per_second_480p": 0.14 }, "runwayml/seedance2_fast": { "litellm_provider": "runwayml", "mode": "video_generation", - "output_cost_per_second": 0.29, + "output_cost_per_second": 0.24, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", @@ -52037,14 +56758,13 @@ "supported_output_modalities": [ "video" ], - "metadata": { - "comment": "29 credits per second at 480p/720p @ $0.01 per credit = $0.29 per second" - } + "metadata": {"comment":"11 credits per second at 480p, 24 at 720p @ $0.01 per credit; 44 credit minimum per generation not modeled"}, + "output_cost_per_second_480p": 0.11 }, "runwayml/seedance2_mini": { "litellm_provider": "runwayml", "mode": "video_generation", - "output_cost_per_second": 0.16, + "output_cost_per_second": 0.15, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", @@ -52054,9 +56774,8 @@ "supported_output_modalities": [ "video" ], - "metadata": { - "comment": "16 credits per second @ $0.01 per credit = $0.16 per second; 64 credit minimum per task not modeled" - } + "metadata": {"comment":"7 credits per second at 480p, 15 at 720p @ $0.01 per credit; 28 credit minimum per generation not modeled"}, + "output_cost_per_second_480p": 0.07 }, "runwayml/seedance2_5": { "litellm_provider": "runwayml", @@ -52077,6 +56796,9 @@ "comment": "Output: 20/30/68 credits per second at 480p/720p/1080p @ $0.01 per credit; input video billed additionally at 10/15/34 credits per input second and the 80 credit minimum per task are not modeled" } }, + "runwayml/seedance-latest": { + "alias_of": "runwayml/seedance2_5" + }, "runwayml/hailuo3": { "litellm_provider": "runwayml", "mode": "video_generation", @@ -52181,14 +56903,11 @@ "runwayml/eleven_multilingual_v2": { "litellm_provider": "runwayml", "mode": "audio_speech", - "input_cost_per_character": 3e-07, + "input_cost_per_character": 0.0002, "source": "https://docs.dev.runwayml.com/guides/pricing/", - "metadata": { - "comment": "Estimated cost based on standard TTS pricing. RunwayML uses ElevenLabs models." - } + "metadata": {"comment":"1 credit per 50 characters @ $0.01 per credit = $0.0002 per character"} }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 4.5e-07, @@ -52198,7 +56917,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/flux-kontext-pro": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 4e-08, @@ -52207,7 +56925,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/SSD-1B": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -52216,7 +56933,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -52225,7 +56941,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -52234,7 +56949,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -52243,7 +56957,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b-python": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -52252,7 +56965,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -52261,7 +56973,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -52270,7 +56981,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b-python": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -52279,7 +56989,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -52288,7 +56997,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -52297,7 +57005,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b-python": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -52306,7 +57013,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -52315,7 +57021,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -52324,7 +57029,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b-python": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -52333,7 +57037,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 2e-07, @@ -52342,7 +57045,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/codegemma-2b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -52351,7 +57053,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/codegemma-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -52360,7 +57061,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.2e-06, @@ -52369,7 +57069,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -52378,7 +57077,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -52387,7 +57085,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -52396,7 +57093,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -52405,7 +57101,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -52414,7 +57109,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-kontext-max": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 8e-08, @@ -52423,7 +57117,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/dbrx-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.2e-06, @@ -52432,7 +57125,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, @@ -52441,7 +57133,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -52450,7 +57141,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -52459,7 +57149,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -52468,7 +57157,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -52477,7 +57165,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, @@ -52486,7 +57173,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, @@ -52495,7 +57181,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-prover-v2": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.2e-06, @@ -52504,7 +57189,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -52513,7 +57197,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -52522,7 +57205,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -52531,7 +57213,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -52540,7 +57221,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -52549,7 +57229,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -52558,7 +57237,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -52567,7 +57245,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, @@ -52576,7 +57253,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-v2p5": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.2e-06, @@ -52585,7 +57261,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/devstral-small-2505": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -52594,7 +57269,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -52603,7 +57277,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -52612,7 +57285,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -52621,7 +57293,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -52630,8 +57301,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, @@ -52639,8 +57309,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, @@ -52648,7 +57317,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/fare-20b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -52657,7 +57325,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firefunction-v1": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -52666,7 +57333,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firellava-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -52675,7 +57341,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -52684,7 +57349,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/fireworks-asr-large": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0.0, @@ -52693,7 +57357,6 @@ "mode": "audio_transcription" }, "fireworks_ai/accounts/fireworks/models/fireworks-asr-v2": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0.0, @@ -52702,7 +57365,6 @@ "mode": "audio_transcription" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -52711,7 +57373,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-09, @@ -52720,7 +57381,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev-fp8": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 5e-10, @@ -52729,7 +57389,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/flux-1-schnell": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -52738,7 +57397,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-schnell-fp8": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 3.5e-10, @@ -52747,7 +57405,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/gemma-2b-it": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -52756,7 +57413,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-3-27b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -52765,7 +57421,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -52774,7 +57429,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-7b-it": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -52783,7 +57437,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma2-9b-it": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -52792,7 +57445,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/glm-4p5v": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.2e-06, @@ -52802,7 +57454,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.2e-06, @@ -52811,7 +57462,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-07, @@ -52820,7 +57470,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -52829,7 +57478,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-38b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -52838,7 +57486,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-78b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -52847,7 +57494,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-8b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -52856,7 +57502,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/japanese-stable-diffusion-xl": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -52865,7 +57510,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/kat-coder": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-07, @@ -52874,7 +57518,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/kat-dev-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -52883,7 +57526,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -52892,7 +57534,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-2-8b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -52901,7 +57542,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-3-1b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -52910,7 +57550,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-3-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -52919,7 +57558,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -52928,7 +57566,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -52937,7 +57574,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-70b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -52946,7 +57582,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat": { - "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 9e-07, @@ -52955,7 +57590,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-7b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -52964,7 +57598,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -52973,7 +57606,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 9e-07, @@ -52982,7 +57614,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 9e-07, @@ -52991,7 +57622,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-8b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -53000,7 +57630,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -53009,7 +57638,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -53018,7 +57646,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53027,7 +57654,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -53036,7 +57662,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53045,7 +57670,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -53054,7 +57678,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -53063,7 +57686,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53072,7 +57694,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llamaguard-7b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -53081,7 +57702,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llava-yi-34b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -53090,7 +57710,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/minimax-m1-80k": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -53099,8 +57718,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/minimax-m2": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 196608, "max_output_tokens": 4096, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, @@ -53108,7 +57726,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 2e-07, @@ -53117,7 +57734,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 1e-07, @@ -53126,7 +57742,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 2e-07, @@ -53135,7 +57750,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53144,7 +57758,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53153,7 +57766,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53162,7 +57774,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53171,7 +57782,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53180,7 +57790,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 1.2e-06, @@ -53189,7 +57798,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -53198,7 +57806,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -53207,7 +57814,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -53216,7 +57822,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 1.2e-06, @@ -53225,7 +57830,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 1.2e-06, @@ -53234,7 +57838,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -53243,7 +57846,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -53252,7 +57854,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -53261,7 +57862,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mythomax-l2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -53270,8 +57870,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, @@ -53279,7 +57878,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53288,7 +57886,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -53297,7 +57894,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -53306,7 +57902,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -53315,7 +57910,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -53324,7 +57918,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -53333,8 +57926,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2": { - "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 128000, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -53342,8 +57934,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2": { - "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 128000, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -53351,7 +57942,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -53360,7 +57950,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53369,7 +57958,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53378,7 +57966,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openorca-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53387,7 +57974,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-2-3b": { - "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 1e-07, @@ -53396,7 +57982,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -53405,7 +57990,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct": { - "max_tokens": 32064, "max_input_tokens": 32064, "max_output_tokens": 32064, "input_cost_per_token": 2e-07, @@ -53414,7 +57998,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -53423,7 +58006,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -53432,7 +58014,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -53441,7 +58022,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/playground-v2-1024px-aesthetic": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -53450,7 +58030,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/playground-v2-5-1024px-aesthetic": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -53459,7 +58038,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/pythia-12b": { - "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 2e-07, @@ -53468,7 +58046,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -53477,7 +58054,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53486,7 +58062,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -53495,7 +58070,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -53504,7 +58078,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53513,7 +58086,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -53522,7 +58094,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -53531,7 +58102,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53540,7 +58110,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -53549,7 +58118,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-14b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -53558,7 +58126,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -53567,7 +58134,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53576,7 +58142,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -53585,7 +58150,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-72b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53594,7 +58158,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -53603,7 +58166,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53612,7 +58174,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -53621,7 +58182,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -53630,7 +58190,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53639,7 +58198,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53648,7 +58206,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -53657,7 +58214,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -53666,7 +58222,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -53675,7 +58230,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53684,7 +58238,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -53693,7 +58246,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 9e-07, @@ -53702,7 +58254,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -53711,7 +58262,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -53720,7 +58270,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53729,7 +58278,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -53738,7 +58286,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -53747,7 +58294,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 9e-07, @@ -53756,7 +58302,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -53765,7 +58310,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 9e-07, @@ -53774,7 +58318,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -53783,7 +58326,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-0p6b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-07, @@ -53792,7 +58334,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-14b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, @@ -53801,7 +58342,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -53810,7 +58350,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-07, @@ -53819,7 +58358,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -53828,7 +58366,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-07, @@ -53837,7 +58374,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.2e-07, @@ -53846,7 +58382,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -53855,7 +58390,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -53864,7 +58398,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, @@ -53873,7 +58406,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-07, @@ -53882,7 +58414,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-07, @@ -53891,7 +58422,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -53901,7 +58431,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/qwen3-4b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, @@ -53910,7 +58439,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-07, @@ -53919,7 +58447,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-8b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, @@ -53929,7 +58456,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -53938,8 +58464,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 262144, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, @@ -53947,7 +58472,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-embedding-0p6b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 0.0, @@ -53956,7 +58480,6 @@ "mode": "embedding" }, "fireworks_ai/accounts/fireworks/models/qwen3-embedding-4b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, @@ -53965,7 +58488,6 @@ "mode": "embedding" }, "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -53974,7 +58496,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -53983,7 +58504,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-0p6b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, @@ -53992,7 +58512,6 @@ "mode": "rerank" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-4b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, @@ -54001,17 +58520,15 @@ "mode": "rerank" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, "output_cost_per_token": 0.0, "litellm_provider": "fireworks_ai", "mode": "rerank", - "source": "https://api.fireworks.ai/v1/serverless/models" + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -54020,7 +58537,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -54029,7 +58545,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -54038,7 +58553,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -54047,7 +58561,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -54056,8 +58569,7 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 262144, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -54070,7 +58582,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -54081,7 +58592,6 @@ "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/qwq-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -54090,7 +58600,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/rolm-ocr": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -54099,7 +58608,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54108,7 +58616,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/stable-diffusion-xl-1024-v1-0": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -54117,7 +58624,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/stablecode-3b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -54126,7 +58632,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder-16b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -54135,7 +58640,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -54144,7 +58648,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-15b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -54153,7 +58656,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-3b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, @@ -54162,7 +58664,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-7b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -54171,7 +58672,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/toppy-m-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54180,7 +58680,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -54189,7 +58688,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 9e-07, @@ -54198,7 +58696,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b-chat": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -54207,7 +58704,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-6b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -54216,7 +58712,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/zephyr-7b-beta": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -54230,7 +58725,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -54243,14 +58737,15 @@ "fireworks_ai/accounts/fireworks/routers/kimi-k2p6-fast": { "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-08-27", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/accounts/fireworks/models/kimi-k2p6", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -54260,14 +58755,15 @@ "fireworks_ai/accounts/fireworks/routers/kimi-k2p7-code-fast": { "cache_read_input_token_cost": 3.8e-07, "deprecation_date": "2026-08-27", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 1.9e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/accounts/fireworks/models/kimi-k2p7-code", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -54279,7 +58775,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-06, "supports_function_calling": true, @@ -54291,7 +58786,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -54303,7 +58797,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.25e-06, "supports_function_calling": true @@ -54319,7 +58812,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, @@ -54330,7 +58822,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true @@ -54346,7 +58837,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 5e-07, "supports_function_calling": true, @@ -54358,7 +58848,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.5e-06, "supports_reasoning": true, @@ -54371,7 +58860,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.5e-07, "supports_function_calling": true, @@ -54382,7 +58870,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, "supports_vision": true, @@ -54400,7 +58887,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 9e-07, "supports_function_calling": true @@ -54412,7 +58898,6 @@ "output_cost_per_token": 4e-07, "max_input_tokens": 163840, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54429,7 +58914,6 @@ "output_cost_per_token": 1.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54445,7 +58929,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54462,7 +58945,6 @@ "output_cost_per_token": 3.3e-07, "max_input_tokens": 262144, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54479,7 +58961,6 @@ "output_cost_per_token": 1.38e-07, "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_vision": true, "supports_system_messages": true }, @@ -54490,7 +58971,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, "max_output_tokens": 100352, - "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54507,7 +58987,6 @@ "output_cost_per_token": 1.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54524,7 +59003,6 @@ "output_cost_per_token": 2e-08, "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_vision": true, "supports_system_messages": true }, @@ -54535,7 +59013,6 @@ "output_cost_per_token": 4.1e-07, "max_input_tokens": 163840, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54550,7 +59027,6 @@ "output_cost_per_token": 3.95e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_vision": true, "supports_system_messages": true, "supports_reasoning": true, @@ -54564,7 +59040,6 @@ "output_cost_per_token": 9e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54582,7 +59057,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54599,7 +59073,6 @@ "output_cost_per_token": 1.2e-06, "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54615,7 +59088,6 @@ "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54630,7 +59102,6 @@ "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54645,7 +59116,6 @@ "output_cost_per_token": 3e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, @@ -54658,7 +59128,6 @@ "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54675,7 +59144,6 @@ "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54690,7 +59158,6 @@ "output_cost_per_token": 8.45e-06, "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54704,7 +59171,6 @@ "output_cost_per_token": 6e-07, "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, @@ -54717,7 +59183,6 @@ "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54734,7 +59199,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, "max_output_tokens": 100352, - "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54748,7 +59212,6 @@ "output_cost_per_token": 1.55e-06, "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54762,7 +59225,6 @@ "output_cost_per_token": 2.7e-07, "max_input_tokens": 160000, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54776,7 +59238,6 @@ "output_cost_per_token": 2.5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54792,7 +59253,6 @@ "output_cost_per_token": 2.3e-06, "max_input_tokens": 131072, "max_output_tokens": 100352, - "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54806,7 +59266,6 @@ "output_cost_per_token": 1.12e-06, "max_input_tokens": 163840, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54822,7 +59281,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 131072, "max_output_tokens": 98304, - "max_tokens": 98304, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54838,7 +59296,6 @@ "output_cost_per_token": 3e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54852,7 +59309,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_system_messages": true, "supports_response_schema": true }, @@ -54863,7 +59319,6 @@ "output_cost_per_token": 1e-07, "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, @@ -54876,7 +59331,6 @@ "output_cost_per_token": 1.8e-06, "max_input_tokens": 65536, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54894,7 +59348,6 @@ "output_cost_per_token": 1.5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_tool_choice": true, "supports_vision": false, "supports_system_messages": true, @@ -54908,7 +59361,6 @@ "output_cost_per_token": 5.8e-07, "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54922,7 +59374,6 @@ "output_cost_per_token": 1.5e-07, "max_input_tokens": 32768, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, @@ -54935,7 +59386,6 @@ "output_cost_per_token": 4e-07, "max_input_tokens": 12288, "max_output_tokens": 12288, - "max_tokens": 12288, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54949,7 +59399,6 @@ "output_cost_per_token": 4e-07, "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54963,7 +59412,6 @@ "output_cost_per_token": 1.7e-07, "max_input_tokens": 60288, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -54975,7 +59423,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 1000000, "max_output_tokens": 40000, - "max_tokens": 40000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -54990,7 +59437,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 163840, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55007,7 +59453,6 @@ "output_cost_per_token": 3e-07, "max_input_tokens": 64000, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, @@ -55020,7 +59465,6 @@ "output_cost_per_token": 4e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_system_messages": true, "supports_response_schema": true }, @@ -55031,7 +59475,6 @@ "output_cost_per_token": 6.2e-07, "max_input_tokens": 65535, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_system_messages": true, "supports_response_schema": true }, @@ -55042,7 +59485,6 @@ "output_cost_per_token": 9e-08, "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_system_messages": true, "supports_reasoning": true }, @@ -55053,7 +59495,6 @@ "output_cost_per_token": 8e-07, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, @@ -55066,7 +59507,6 @@ "output_cost_per_token": 7.4e-07, "max_input_tokens": 8192, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -55078,7 +59518,6 @@ "output_cost_per_token": 8e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true @@ -55090,7 +59529,6 @@ "output_cost_per_token": 8.5e-07, "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true @@ -55102,7 +59540,6 @@ "output_cost_per_token": 5.9e-07, "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_vision": true, "supports_system_messages": true }, @@ -55113,7 +59550,6 @@ "output_cost_per_token": 1.4e-07, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -55125,7 +59561,6 @@ "output_cost_per_token": 8e-07, "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_vision": true, "supports_system_messages": true }, @@ -55136,7 +59571,6 @@ "output_cost_per_token": 1.48e-06, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55149,7 +59583,6 @@ "output_cost_per_token": 2.8e-07, "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_system_messages": true, "supports_reasoning": true }, @@ -55160,7 +59593,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -55172,7 +59604,6 @@ "output_cost_per_token": 7e-08, "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-424b-a47b": { @@ -55182,7 +59613,6 @@ "output_cost_per_token": 1.25e-06, "max_input_tokens": 123000, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_vision": true, "supports_system_messages": true, "supports_reasoning": true @@ -55194,7 +59624,6 @@ "output_cost_per_token": 1.1e-06, "max_input_tokens": 123000, "max_output_tokens": 12000, - "max_tokens": 12000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -55206,7 +59635,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 160000, "max_output_tokens": 160000, - "max_tokens": 160000, "supports_system_messages": true }, "novita/qwen/qwen3-32b-fp8": { @@ -55216,7 +59644,6 @@ "output_cost_per_token": 4.5e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true }, @@ -55227,7 +59654,6 @@ "output_cost_per_token": 4.5e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "supports_function_calling": true, @@ -55240,7 +59666,6 @@ "output_cost_per_token": 2e-07, "max_input_tokens": 98304, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_vision": true, "supports_system_messages": true }, @@ -55251,7 +59676,6 @@ "output_cost_per_token": 1.3e-06, "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55264,7 +59688,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55279,7 +59702,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 8192, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55292,7 +59714,6 @@ "output_cost_per_token": 9e-08, "max_input_tokens": 4096, "max_output_tokens": 3200, - "max_tokens": 3200, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-28b-a3b-thinking": { @@ -55302,7 +59723,6 @@ "output_cost_per_token": 3.9e-07, "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55318,7 +59738,6 @@ "output_cost_per_token": 5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55333,7 +59752,6 @@ "output_cost_per_token": 8.5e-07, "max_input_tokens": 131072, "max_output_tokens": 98304, - "max_tokens": 98304, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55349,7 +59767,6 @@ "output_cost_per_token": 7e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55364,7 +59781,6 @@ "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55379,7 +59795,6 @@ "output_cost_per_token": 9.7e-07, "max_input_tokens": 65536, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55396,7 +59811,6 @@ "output_cost_per_token": 9.7e-07, "max_input_tokens": 65536, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55413,7 +59827,6 @@ "output_cost_per_token": 7.5e-07, "max_input_tokens": 16384, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-28b-a3b": { @@ -55423,7 +59836,6 @@ "output_cost_per_token": 5.6e-07, "max_input_tokens": 30000, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55438,7 +59850,6 @@ "output_cost_per_token": 2.8e-07, "max_input_tokens": 120000, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55451,7 +59862,6 @@ "output_cost_per_token": 1.38e-07, "max_input_tokens": 128000, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true }, @@ -55462,7 +59872,6 @@ "output_cost_per_token": 3e-08, "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_system_messages": true, "supports_reasoning": true, "supports_function_calling": true, @@ -55475,7 +59884,6 @@ "output_cost_per_token": 7e-08, "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55489,7 +59897,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 32768, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55502,7 +59909,6 @@ "output_cost_per_token": 1.48e-06, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -55514,8 +59920,7 @@ "input_cost_per_token": 7e-08, "output_cost_per_token": 0, "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768 + "max_output_tokens": 32768 }, "novita/qwen/qwen3-embedding-8b": { "litellm_provider": "novita", @@ -55523,8 +59928,7 @@ "input_cost_per_token": 7e-08, "output_cost_per_token": 0, "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096 + "max_output_tokens": 4096 }, "novita/baai/bge-m3": { "litellm_provider": "novita", @@ -55532,8 +59936,7 @@ "input_cost_per_token": 1e-08, "output_cost_per_token": 1e-08, "max_input_tokens": 8192, - "max_output_tokens": 96000, - "max_tokens": 96000 + "max_output_tokens": 96000 }, "novita/qwen/qwen3-reranker-8b": { "litellm_provider": "novita", @@ -55541,8 +59944,7 @@ "input_cost_per_token": 5e-08, "output_cost_per_token": 5e-08, "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096 + "max_output_tokens": 4096 }, "novita/baai/bge-reranker-v2-m3": { "litellm_provider": "novita", @@ -55550,11 +59952,9 @@ "input_cost_per_token": 1e-08, "output_cost_per_token": 1e-08, "max_input_tokens": 8000, - "max_output_tokens": 8000, - "max_tokens": 8000 + "max_output_tokens": 8000 }, "llamagate/llama-3.1-8b": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, @@ -55565,7 +59965,6 @@ "supports_response_schema": true }, "llamagate/llama-3.2-3b": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, @@ -55576,7 +59975,6 @@ "supports_response_schema": true }, "llamagate/mistral-7b-v0.3": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -55587,7 +59985,6 @@ "supports_response_schema": true }, "llamagate/qwen3-8b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, @@ -55598,7 +59995,6 @@ "supports_response_schema": true }, "llamagate/dolphin3-8b": { - "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 8e-08, @@ -55609,7 +60005,6 @@ "supports_response_schema": true }, "llamagate/deepseek-r1-8b": { - "max_tokens": 16384, "max_input_tokens": 65536, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, @@ -55621,7 +60016,6 @@ "supports_reasoning": true }, "llamagate/deepseek-r1-7b-qwen": { - "max_tokens": 16384, "max_input_tokens": 131072, "max_output_tokens": 16384, "input_cost_per_token": 8e-08, @@ -55633,7 +60027,6 @@ "supports_reasoning": true }, "llamagate/openthinker-7b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 8e-08, @@ -55645,7 +60038,6 @@ "supports_reasoning": true }, "llamagate/qwen2.5-coder-7b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 6e-08, @@ -55656,7 +60048,6 @@ "supports_response_schema": true }, "llamagate/deepseek-coder-6.7b": { - "max_tokens": 4096, "max_input_tokens": 16384, "max_output_tokens": 4096, "input_cost_per_token": 6e-08, @@ -55667,7 +60058,6 @@ "supports_response_schema": true }, "llamagate/codellama-7b": { - "max_tokens": 4096, "max_input_tokens": 16384, "max_output_tokens": 4096, "input_cost_per_token": 6e-08, @@ -55678,7 +60068,6 @@ "supports_response_schema": true }, "llamagate/qwen3-vl-8b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 1.5e-07, @@ -55690,7 +60079,6 @@ "supports_vision": true }, "llamagate/llava-7b": { - "max_tokens": 2048, "max_input_tokens": 4096, "max_output_tokens": 2048, "input_cost_per_token": 1e-07, @@ -55701,7 +60089,6 @@ "supports_vision": true }, "llamagate/gemma3-4b": { - "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, @@ -55713,7 +60100,6 @@ "supports_vision": true }, "llamagate/nomic-embed-text": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 2e-08, "output_cost_per_token": 0, @@ -55721,7 +60107,6 @@ "mode": "embedding" }, "llamagate/qwen3-embedding-8b": { - "max_tokens": 40960, "max_input_tokens": 40960, "input_cost_per_token": 2e-08, "output_cost_per_token": 0, @@ -55729,7 +60114,6 @@ "mode": "embedding" }, "libertai/hermes-3-8b-tee": { - "max_tokens": 16000, "max_input_tokens": 16000, "max_output_tokens": 16000, "input_cost_per_token": 1.5e-07, @@ -55743,7 +60127,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/gemma-4-31b-it": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -55757,7 +60140,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/gemma-4-31b-it-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -55772,7 +60154,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-27b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -55786,7 +60167,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-27b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -55801,7 +60181,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-35b-a3b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -55815,7 +60194,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-35b-a3b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -55830,7 +60208,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.5-122b-a10b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.5e-07, @@ -55844,7 +60221,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.5-122b-a10b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.5e-07, @@ -55859,7 +60235,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/deepseek-v4-flash": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 2.5e-07, @@ -55873,7 +60248,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/deepseek-v4-flash-thinking": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 2.5e-07, @@ -55888,7 +60262,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/bge-m3": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -55904,7 +60277,6 @@ "litellm_provider": "sarvam", "max_input_tokens": 8192, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0, "supports_reasoning": true @@ -55927,6 +60299,8 @@ }, "gpt-4o-mini-tts-2025-12-15": { "deprecation_date": "2027-01-06", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", @@ -55947,6 +60321,8 @@ }, "gpt-4o-mini-transcribe-2025-03-20": { "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-4o-mini-transcribe-2025-12-15", "input_cost_per_audio_token": 1.25e-06, "input_cost_per_second": 5e-05, "input_cost_per_token": 1.25e-06, @@ -55961,6 +60337,9 @@ ] }, "gpt-4o-mini-transcribe-2025-12-15": { + "deprecation_date": "2027-02-26", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-live-transcribe", "input_cost_per_audio_token": 1.25e-06, "input_cost_per_second": 5e-05, "input_cost_per_token": 1.25e-06, @@ -55980,9 +60359,9 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -56008,9 +60387,9 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -56040,7 +60419,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -56063,6 +60441,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "deprecation_date": "2027-01-20", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-realtime-2.1-mini", "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-realtime-whisper": { @@ -56084,6 +60464,7 @@ }, "sora-2": { "deprecation_date": "2026-09-24", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, @@ -56098,6 +60479,7 @@ }, "sora-2-pro": { "deprecation_date": "2026-09-24", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.3, @@ -56113,6 +60495,7 @@ "sora-2-pro-high-res": { "litellm_provider": "openai", "deprecation_date": "2026-09-24", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "mode": "video_generation", "output_cost_per_video_per_second": 0.5, "source": "https://developers.openai.com/api/docs/pricing", @@ -56126,9 +60509,12 @@ }, "chatgpt-image-latest": { "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.3e-07, "deprecation_date": "2026-12-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image_token": 8e-06, "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token": 5e-06, @@ -56136,6 +60522,7 @@ "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, + "output_cost_per_image_token_batches": 1.6e-05, "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", @@ -56144,55 +60531,12 @@ "/v1/images/edits" ] }, - "gemini-2.0-flash-exp-image-generation": { - "input_cost_per_token": 0.0, - "litellm_provider": "gemini", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.039, - "output_cost_per_token": 0.0, - "source": "https://ai.google.dev/pricing", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_vision": true - }, - "gemini/gemini-2.0-flash-exp-image-generation": { - "input_cost_per_token": 0.0, - "litellm_provider": "gemini", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.039, - "output_cost_per_token": 0.0, - "source": "https://ai.google.dev/pricing", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_vision": true, - "tpm": 250000, - "rpm": 10 - }, "gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -56218,7 +60562,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -56240,12 +60583,13 @@ }, "gemini-2.5-flash-native-audio-preview-12-2025": { "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -56264,6 +60608,7 @@ "supports_audio_input": true, "supports_audio_output": true, "gemini_native_audio": true, + "input_cost_per_video_token": 3e-06, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, @@ -56271,6 +60616,8 @@ }, "gemini-3.1-flash-live-preview": { "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, @@ -56279,7 +60626,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -56314,7 +60660,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -56348,7 +60693,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -56381,7 +60725,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -56409,7 +60752,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -56433,12 +60775,13 @@ }, "gemini/gemini-2.5-flash-native-audio-preview-12-2025": { "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -56459,6 +60802,7 @@ "tpm": 250000, "rpm": 10, "gemini_native_audio": true, + "input_cost_per_video_token": 3e-06, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, @@ -56467,6 +60811,8 @@ }, "gemini/gemini-3.1-flash-live-preview": { "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, @@ -56475,7 +60821,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -56502,17 +60847,19 @@ "rpm": 10, "gemini_audio_only_live": true, "input_cost_per_second": 8.33333333333e-05, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "supports_response_schema": false, "supports_reasoning": true }, "gemini/gemini-3.1-flash-tts-preview": { "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-flash-tts", "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, @@ -56539,7 +60886,6 @@ "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 9e-06, "output_cost_per_token": 9e-06, @@ -56564,7 +60910,6 @@ "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 6e-06, "output_cost_per_token": 6e-06, @@ -56579,12 +60924,13 @@ }, "gemini-2.5-flash-preview-tts": { "deprecation_date": "2026-11-17", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", + "successor_model": "gemini/gemini-3.8-flash-tts", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, @@ -56600,11 +60946,11 @@ }, "gemini-flash-latest": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "input_cost_per_token": 7.5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -56659,11 +61005,11 @@ }, "gemini-flash-lite-latest": { "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_batches": 1.5e-08, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -56718,12 +61064,13 @@ "gemini-pro-latest": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_flex": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, @@ -56762,6 +61109,7 @@ }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_batches": 2e-07, "cache_read_input_token_cost_priority": 3.6e-07, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, @@ -56774,18 +61122,23 @@ "supports_url_context": true, "web_search_billing_unit": "per_query", "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_above_200k_tokens_flex": 2e-06, "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_above_200k_tokens_batches": 9e-06, + "output_cost_per_token_above_200k_tokens_flex": 9e-06, "output_cost_per_token_flex": 6e-06 }, "gemini/gemini-pro-latest": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_flex": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, @@ -56824,6 +61177,7 @@ }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_batches": 2e-07, "cache_read_input_token_cost_priority": 3.6e-07, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, @@ -56836,7 +61190,11 @@ "supports_url_context": true, "web_search_billing_unit": "per_query", "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_above_200k_tokens_flex": 2e-06, "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_above_200k_tokens_batches": 9e-06, + "output_cost_per_token_above_200k_tokens_flex": 9e-06, "output_cost_per_token_flex": 6e-06 }, "gemini-exp-1206": { @@ -56846,7 +61204,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -56897,7 +61254,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -56907,6 +61263,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -56936,11 +61293,10 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -56968,16 +61324,20 @@ } }, "bedrock_mantle/openai.gpt-oss-120b": { + "supports_vision": false, "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -56989,16 +61349,20 @@ "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-oss-20b": { + "supports_vision": false, "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3.5e-08, "input_cost_per_token_flex": 3.5e-08, + "input_cost_per_token_priority": 1.225e-07, "output_cost_per_token": 3e-07, "output_cost_per_token_flex": 1.5e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", + "output_cost_per_token_batches": 1.5e-07, + "output_cost_per_token_priority": 5.25e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -57010,16 +61374,20 @@ "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-oss-safeguard-120b": { + "supports_vision": false, "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7e-08, "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "output_cost_per_token": 6e-07, "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-safeguard-120b.html", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], @@ -57029,16 +61397,20 @@ "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-oss-safeguard-20b": { + "supports_vision": false, "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3e-08, "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.2e-07, "output_cost_per_token": 2e-07, "output_cost_per_token_flex": 1e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-safeguard-20b.html", + "output_cost_per_token_batches": 1e-07, + "output_cost_per_token_priority": 3.5e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], @@ -57062,9 +61434,8 @@ "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -57106,9 +61477,8 @@ "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -57141,12 +61511,14 @@ "cache_read_input_token_cost": 1.375e-06, "output_cost_per_token": 8.25e-05, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 272000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-cyber.html", "use_openai_responses_path": true, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ @@ -57164,7 +61536,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, "bedrock_mantle/openai.gpt-daybreak-blue-5.6-sol": { "input_cost_per_token": 4.4e-06, @@ -57176,10 +61549,10 @@ "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1000000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" @@ -57199,7 +61572,8 @@ "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-daybreak-blue-56-sol.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-daybreak-blue-56-sol.html", + "supports_web_search": true }, "bedrock_mantle/openai.gpt-5.6-luna": { "input_cost_per_token": 2.2e-07, @@ -57216,9 +61590,8 @@ "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -57257,9 +61630,8 @@ "output_cost_per_token_above_272k_tokens": 3.3e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "supported_modalities": [ @@ -57294,9 +61666,8 @@ "output_cost_per_token_above_272k_tokens": 3e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "supported_modalities": [ @@ -57331,9 +61702,8 @@ "output_cost_per_token_above_272k_tokens": 1.98e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "supported_modalities": [ @@ -57368,9 +61738,8 @@ "output_cost_per_token_above_272k_tokens": 1.8e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "supported_modalities": [ @@ -57405,9 +61774,8 @@ "output_cost_per_token_above_272k_tokens": 1.98e-06, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "supported_modalities": [ @@ -57439,9 +61807,8 @@ "output_cost_per_token_above_272k_tokens": 2.475e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "supported_modalities": [ @@ -57471,9 +61838,8 @@ "output_cost_per_token_above_272k_tokens": 2.25e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "supported_modalities": [ @@ -57503,9 +61869,8 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html", "supported_modalities": [ @@ -57535,9 +61900,8 @@ "output_cost_per_token_above_272k_tokens": 4.5e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html", "supported_modalities": [ @@ -57570,9 +61934,8 @@ "output_cost_per_token_above_272k_tokens": 1.8e-06, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "supported_modalities": [ @@ -57611,12 +61974,12 @@ "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495, "output_cost_per_token_ultrafast": 0.00033, + "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -57640,7 +62003,11 @@ "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", + "supports_web_search": true + }, + "bedrock_mantle/gpt-astra-latest": { + "alias_of": "bedrock_mantle/openai.gpt-6-astra" }, "bedrock_mantle/openai.gpt-6-sol": { "input_cost_per_token": 2.2e-06, @@ -57652,10 +62019,10 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -57671,7 +62038,7 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_prompt_caching": true, "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, @@ -57679,7 +62046,8 @@ "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html", + "supports_web_search": true }, "bedrock_mantle/openai.gpt-6-luna": { "input_cost_per_token": 1.1e-07, @@ -57691,10 +62059,10 @@ "output_cost_per_token": 5.5e-07, "output_cost_per_token_above_272k_tokens": 8.25e-07, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", + "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -57710,7 +62078,7 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_prompt_caching": true, "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, @@ -57718,7 +62086,11 @@ "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html", + "supports_web_search": true + }, + "bedrock_mantle/gpt-luna-latest": { + "alias_of": "bedrock_mantle/openai.gpt-6-luna" }, "us.openai.gpt-6-astra": { "supports_bedrock_runtime_chat_completions_response_format": true, @@ -57738,9 +62110,8 @@ "output_cost_per_token_above_272k_tokens": 8.25e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495, "output_cost_per_token_ultrafast": 0.00033, @@ -57779,9 +62150,8 @@ "output_cost_per_token_above_272k_tokens": 1.65e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -57793,7 +62163,7 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -57818,9 +62188,8 @@ "output_cost_per_token_above_272k_tokens": 8.25e-07, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -57832,7 +62201,7 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -57863,9 +62232,8 @@ "output_cost_per_token_above_272k_tokens": 7.5e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045, "output_cost_per_token_ultrafast": 0.0003, @@ -57892,6 +62260,9 @@ "/v1/responses" ] }, + "bedrock/gpt-astra-latest": { + "alias_of": "global.openai.gpt-6-astra" + }, "openai.gpt-6-sol": { "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, @@ -57903,9 +62274,8 @@ "output_cost_per_token_above_272k_tokens": 1.5e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -57917,7 +62287,7 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -57938,9 +62308,8 @@ "output_cost_per_token_above_272k_tokens": 1.5e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -57952,7 +62321,7 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -57976,9 +62345,8 @@ "output_cost_per_token_above_272k_tokens": 7.5e-07, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -57990,7 +62358,7 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -58011,9 +62379,8 @@ "output_cost_per_token_above_272k_tokens": 7.5e-07, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -58025,7 +62392,7 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -58038,6 +62405,9 @@ "/v1/responses" ] }, + "bedrock/gpt-luna-latest": { + "alias_of": "global.openai.gpt-6-luna" + }, "bedrock_mantle/openai.gpt-5.5": { "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, @@ -58051,9 +62421,8 @@ "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -58091,9 +62460,8 @@ "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -58120,14 +62488,18 @@ }, "bedrock_mantle/google.gemma-4-31b": { "input_cost_per_token": 1.4e-07, + "input_cost_per_token_batches": 7e-08, "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.45e-07, "output_cost_per_token": 4e-07, "output_cost_per_token_flex": 2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_priority": 7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58141,14 +62513,18 @@ }, "bedrock_mantle/google.gemma-4-26b-a4b": { "input_cost_per_token": 1.3e-07, + "input_cost_per_token_batches": 6.5e-08, "input_cost_per_token_flex": 6.5e-08, + "input_cost_per_token_priority": 2.275e-07, "output_cost_per_token": 4e-07, "output_cost_per_token_flex": 2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_priority": 7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58162,14 +62538,18 @@ }, "bedrock_mantle/google.gemma-4-e2b": { "input_cost_per_token": 4e-08, + "input_cost_per_token_batches": 2e-08, "input_cost_per_token_flex": 2e-08, + "input_cost_per_token_priority": 7e-08, "output_cost_per_token": 8e-08, "output_cost_per_token_flex": 4e-08, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 4e-08, + "output_cost_per_token_priority": 1.4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58186,15 +62566,17 @@ "input_cost_per_token": 1.25e-06, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, "input_cost_per_token_priority": 2.1875e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 1048576, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", + "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_flex": 1.25e-06, "output_cost_per_token_priority": 4.375e-06, "supported_endpoints": [ @@ -58206,7 +62588,7 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/xai.grok-4.6": { "use_openai_responses_path": true, @@ -58220,7 +62602,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token_flex": 3.3e-06, "output_cost_per_token_priority": 1.155e-05, @@ -58245,7 +62626,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -58262,7 +62642,8 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-07, - "output_cost_per_token_batches": 2.5e-06 + "output_cost_per_token_batches": 2.5e-06, + "token_count_model": {"model":"anthropic.claude-haiku-4-5-20251001-v1:0","litellm_provider":"bedrock"} }, "bedrock_mantle/anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -58276,7 +62657,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { @@ -58302,7 +62682,11 @@ "prompt_cache_min_tokens": 512, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html", "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": {"model":"anthropic.claude-opus-5-5","litellm_provider":"bedrock_mantle","region":"us-east-1"} + }, + "bedrock_mantle/claude-opus-latest": { + "alias_of": "bedrock_mantle/anthropic.claude-opus-5-5" }, "bedrock_mantle/anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -58314,7 +62698,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { @@ -58345,6 +62728,9 @@ "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, + "bedrock_mantle/claude-sonnet-latest": { + "alias_of": "bedrock_mantle/anthropic.claude-sonnet-5-5" + }, "us.xai.grok-4.6": { "supports_regex_lookaround": false, "input_cost_per_token": 2.2e-06, @@ -58362,7 +62748,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token_flex": 3.3e-06, "output_cost_per_token_priority": 1.155e-05, @@ -58390,7 +62775,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token_flex": 3e-06, "output_cost_per_token_priority": 1.05e-05, @@ -58405,7 +62789,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -58445,7 +62828,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4.3125e-06, "source": "https://www.volcengine.com/docs/82379/1544106", @@ -58455,13 +62837,45 @@ "supports_tool_choice": false, "supports_vision": true }, + "volcengine/doubao-seed-2-1-pro-260915": { + "cache_read_input_token_cost": 1.725e-07, + "input_cost_per_token": 8.625e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 1024000, + "max_output_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4.3125e-06, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "volcengine/doubao-seed-2-1-lite-260915": { + "cache_read_input_audio_token_cost": 3.45e-07, + "cache_read_input_token_cost": 2.3e-08, + "input_cost_per_audio_token": 1.725e-06, + "input_cost_per_token": 1.15e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 1024000, + "max_output_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 3.88126e-07, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, "volcengine/doubao-seed-2-1-turbo-260628": { "cache_read_input_token_cost": 8.625e-08, "input_cost_per_token": 4.3125e-07, "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.15625e-06, "source": "https://www.volcengine.com/docs/82379/1544106", @@ -58475,7 +62889,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -58513,7 +62926,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -58551,7 +62963,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -58585,14 +62996,74 @@ } ] }, + "volcengine/doubao-seedance-2-5-260628": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.216, + "output_cost_per_second_480p": 0.096075, + "output_cost_per_second_720p": 0.216, + "output_cost_per_second_1080p": 0.5346, + "supported_modalities": ["text", "image", "video", "audio"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "854x480", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "480x854", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s). List 70 CNY per million tokens at 480p and 720p and 77 at 1080p without a video input, matching Ark's per-resolution table and its 1080p 16:9 example of 3.74 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Accepts up to 50 reference assets (30 images, 10 videos, 10 audios) and clips of 4-30s; per-asset billing beyond the free allowance is not encoded. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, + "volcengine/doubao-seedance-2-0-260128": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.141942857, + "output_cost_per_second_480p": 0.066003429, + "output_cost_per_second_720p": 0.141942857, + "output_cost_per_second_1080p": 0.354085714, + "output_cost_per_second_4k": 0.722057143, + "supported_modalities": ["text", "image", "video", "audio"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 46 CNY per million tokens at 480p and 720p, 51 at 1080p, and 26 at 4k without a video input, matching Ark's per-resolution table and its 1080p and 4k 16:9 examples of 2.48 and 5.05 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s; 4k is exclusive to this tier. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, + "volcengine/doubao-seedance-2-0-fast-260128": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.114171429, + "output_cost_per_second_480p": 0.053089714, + "output_cost_per_second_720p": 0.114171429, + "supported_modalities": ["text", "image", "video", "audio"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 37 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, + "volcengine/doubao-seedance-2-0-mini-260615": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.070971429, + "output_cost_per_second_480p": 0.033001714, + "output_cost_per_second_720p": 0.070971429, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 23 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Only text and image inputs are declared; the mini tier's reference video and audio caps were not verified. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, "bedrock/us-east-1/zai.glm-5": { "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "input_cost_per_token_flex": 5e-07, + "input_cost_per_token_priority": 1.75e-06, "output_cost_per_token": 3.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 1.6e-06, + "output_cost_per_token_flex": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -58601,16 +63072,21 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-west-2/zai.glm-5": { "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "input_cost_per_token_flex": 5e-07, + "input_cost_per_token_priority": 1.75e-06, "output_cost_per_token": 3.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 1.6e-06, + "output_cost_per_token_flex": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -58619,7 +63095,7 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.5e-06, @@ -58630,7 +63106,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -58645,7 +63120,11 @@ "supports_native_structured_output": true, "supports_pdf_input": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.5e-06, @@ -58656,7 +63135,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -58671,10 +63149,13 @@ "supports_native_structured_output": true, "supports_pdf_input": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "snowflake/claude-sonnet-4-5": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -58692,7 +63173,6 @@ "snowflake/claude-sonnet-4-6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -58708,7 +63188,6 @@ "prompt_cache_min_tokens": 1024 }, "snowflake/claude-4-sonnet": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -58724,7 +63203,6 @@ "prompt_cache_min_tokens": 1024 }, "snowflake/claude-4-opus": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 5e-06, @@ -58741,7 +63219,6 @@ "prompt_cache_min_tokens": 1024 }, "snowflake/claude-haiku-4-5": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 1e-06, @@ -58757,7 +63234,6 @@ "prompt_cache_min_tokens": 4096 }, "snowflake/claude-3-7-sonnet": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -58773,7 +63249,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-4.1": { - "max_tokens": 16384, "max_input_tokens": 300000, "max_output_tokens": 16384, "input_cost_per_token": 2e-06, @@ -58788,7 +63263,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-5": { - "max_tokens": 16384, "max_input_tokens": 300000, "max_output_tokens": 16384, "input_cost_per_token": 1.25e-06, @@ -58804,7 +63278,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-5-mini": { - "max_tokens": 16384, "max_input_tokens": 1000000, "max_output_tokens": 16384, "input_cost_per_token": 3e-07, @@ -58816,7 +63289,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-5-nano": { - "max_tokens": 16384, "max_input_tokens": 5000000, "max_output_tokens": 16384, "input_cost_per_token": 1.5e-07, @@ -58828,7 +63300,6 @@ "supports_response_schema": true }, "snowflake/llama4-maverick": { - "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 2.4e-07, @@ -58839,7 +63310,6 @@ "supports_system_messages": true }, "snowflake/snowflake-arctic-embed-l-v2.0": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 7e-08, "output_cost_per_token": 0.0, @@ -58847,7 +63317,6 @@ "mode": "embedding" }, "snowflake/snowflake-arctic-embed-m-v2.0": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 7e-08, "output_cost_per_token": 0.0, @@ -58857,7 +63326,7 @@ "soniox/stt-async-v4": { "litellm_provider": "soniox", "max_output_tokens": 8000, - "max_tokens": 8000, + "max_input_tokens": 8000, "input_cost_per_second": 0.0, "output_cost_per_second": 2.77778e-05, "mode": "audio_transcription", @@ -58870,7 +63339,7 @@ "soniox/stt-async-v5": { "litellm_provider": "soniox", "max_output_tokens": 8000, - "max_tokens": 8000, + "max_input_tokens": 8000, "input_cost_per_second": 0.0, "output_cost_per_second": 2.77778e-05, "mode": "audio_transcription", @@ -58880,6 +63349,126 @@ ], "supports_audio_input": true }, + "soniox/stt-rt-v5": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "soniox", + "metadata": { + "calculation": "$0.12/3600 seconds = $0.00003333 per second", + "original_pricing_per_hour": 0.12 + }, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "soniox/stt-rt-preview": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "soniox", + "metadata": { + "calculation": "$0.12/3600 seconds = $0.00003333 per second", + "original_pricing_per_hour": 0.12 + }, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "soniox/stt-rt-preview-v2": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "soniox", + "metadata": { + "calculation": "$0.12/3600 seconds = $0.00003333 per second", + "original_pricing_per_hour": 0.12 + }, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "soniox/stt-rt-v3": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "soniox", + "metadata": { + "calculation": "$0.12/3600 seconds = $0.00003333 per second", + "original_pricing_per_hour": 0.12 + }, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "soniox/stt-rt-v3-preview": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "soniox", + "metadata": { + "calculation": "$0.12/3600 seconds = $0.00003333 per second", + "original_pricing_per_hour": 0.12 + }, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "soniox/stt-rt-v4": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "soniox", + "metadata": { + "calculation": "$0.12/3600 seconds = $0.00003333 per second", + "original_pricing_per_hour": 0.12 + }, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, "tensormesh/Qwen/Qwen3.5-397B-A17B-FP8": { "litellm_provider": "tensormesh", "mode": "chat", @@ -59047,7 +63636,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -59093,6 +63681,359 @@ "supports_tool_choice": true, "supports_vision": true }, + "streamlake/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 1.32e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 1048566, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/DeepSeek-V3": { + "cache_read_input_token_cost": 1.14e-07, + "input_cost_per_token": 2.86e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 56000, + "max_output_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.143e-06, + "supports_function_calling": true, + "supports_reasoning": false, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/GLM-5.3": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_assistant_prefill": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/GLM-5.3-Flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_assistant_prefill": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/Kimi-K2-Instruct-0905": { + "cache_read_input_token_cost": 1.43e-07, + "input_cost_per_token": 5.71e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 224000, + "max_output_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.286e-06, + "supports_function_calling": true, + "supports_reasoning": false, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/deepseek-r1": { + "cache_read_input_token_cost": 2.29e-07, + "input_cost_per_token": 5.71e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 98304, + "max_output_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 2.286e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/deepseek-v3.1": { + "cache_read_input_token_cost": 2.29e-07, + "input_cost_per_token": 5.71e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 98304, + "max_output_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.714e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/deepseek-v4-flash": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/deepseek-v4-pro": { + "cache_read_input_token_cost": 1.45e-07, + "input_cost_per_token": 1.74e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.48e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/deepseek-v4.1-flash-1017": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/deepseek-v4.1-flash-260910": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 1048568, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/glm-5": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 202752, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/glm-5.1": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 202752, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/glm-5.2": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 1048566, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/kimi-k2.6": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 262144, + "max_output_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_function_calling": true, + "supports_vision": true, + "supports_reasoning": false, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 262144, + "max_output_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/mimo-v2.6-flash": { + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "streamlake", + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/mimo-v2.6-pro": { + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 4.35e-07, + "litellm_provider": "streamlake", + "mode": "chat", + "output_cost_per_token": 8.7e-07, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/minimax-m2.5": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 196608, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/minimax-m3": { + "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_above_512k_tokens": 2.4e-07, + "input_cost_per_token": 6e-07, + "input_cost_per_token_above_512k_tokens": 1.2e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 1000000, + "max_output_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "output_cost_per_token_above_512k_tokens": 4.8e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/qwen3.5-397b-a17b": { + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 258048, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/qwen3.6-27b": { + "input_cost_per_token": 6e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 229376, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "supports_function_calling": true, + "supports_vision": true, + "supports_reasoning": false, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/qwen3.6-35b-a3b": { + "input_cost_per_token": 3.75e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 229376, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.25e-06, + "supports_function_calling": true, + "supports_vision": true, + "supports_reasoning": false, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/qwen3.8-2.4t-a95b": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "streamlake", + "max_input_tokens": 983616, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "cache_creation_input_token_cost": 2.5e-06, + "explicit_cache_read_input_token_cost": 1.7e-07, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, + "streamlake/qwen3.8-27b": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 5e-07, + "litellm_provider": "streamlake", + "max_input_tokens": 983616, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "cache_creation_input_token_cost": 6.25e-07, + "explicit_cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" + }, "deepseek-v4-flash": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 6e-09, @@ -59101,7 +64042,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -59155,7 +64095,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -59209,7 +64148,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 2.2e-08, @@ -59263,7 +64201,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -59317,7 +64254,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -59361,7 +64297,12 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "token_count_framing": 23, + "token_count_tool_framing": 12 + }, + "deepseek/deepseek-flash-latest": { + "alias_of": "deepseek/deepseek-v4-flash" }, "deepseek/deepseek-v4-flash-vision-exp": { "cache_creation_input_token_cost": 0.0, @@ -59371,7 +64312,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -59425,7 +64365,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 2.2e-08, @@ -59469,20 +64408,24 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "token_count_framing": 76, + "token_count_tool_framing": 75 + }, + "deepseek/deepseek-pro-latest": { + "alias_of": "deepseek/deepseek-v4-pro" }, "tencent/deepseek-v4-pro": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 3.625e-09, - "input_cost_per_token": 4.35e-07, - "input_cost_per_token_cache_hit": 3.625e-09, + "cache_read_input_token_cost": 1.45e-07, + "input_cost_per_token": 1.74e-06, + "input_cost_per_token_cache_hit": 1.45e-07, "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 8.7e-07, - "source": "https://www.tencentcloud.com/products/tokenhub", + "output_cost_per_token": 3.48e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], @@ -59505,10 +64448,117 @@ "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, - "source": "https://www.tencentcloud.com/products/tokenhub", + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "tencent/deepseek-v4-pro-0813": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 1.32e-06, + "input_cost_per_token_cache_hit": 4.4e-08, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 6.6e-07, + "output_cost_per_token": 1.98e-06, + "weekday_timezone": "Asia/Shanghai", + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 3.96e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "tencent/deepseek-v4.1-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_cache_hit": 6e-09, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "weekday_timezone": "Asia/Shanghai", + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 1.2e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], @@ -59521,8 +64571,227 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_reasoning": true, + "supports_vision": true + }, + "tencent/glm-5.3-flashx": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 3.7e-07, + "input_cost_per_token_cache_hit": 7.5e-08, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "tencent/glm-5.3-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_cache_hit": 3e-08, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "tencent/glm-5.3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "input_cost_per_token_cache_hit": 2.6e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/glm-5.2": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "input_cost_per_token_cache_hit": 2.6e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, "supports_vision": false }, + "tencent/kimi-k3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_cache_hit": 3e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k2.8-preview": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_cache_hit": 2.5e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k2.7-code-highspeed": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3.8e-07, + "input_cost_per_token": 1.9e-06, + "input_cost_per_token_cache_hit": 3.8e-07, + "litellm_provider": "tencent", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k2.7-code": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "input_cost_per_token_cache_hit": 1.9e-07, + "litellm_provider": "tencent", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/hy4": { + "cache_read_input_token_cost": 2.1e-08, + "comment": "These are the 50% promotional rates. Update on 2026-12-31 when the promotion ends at 23:59:59 Beijing time. List rates per 1M tokens are $0.834 input, $2.501 output and $0.042 cached input.", + "input_cost_per_token": 4.17e-07, + "input_cost_per_token_cache_hit": 2.1e-08, + "litellm_provider": "tencent", + "max_input_tokens": 960000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.2505e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "tencent/hy4-preview": { + "cache_read_input_token_cost": 2.1e-08, + "comment": "These are the 50% promotional rates. Update on 2026-12-31 when the promotion ends at 23:59:59 Beijing time. List rates per 1M tokens are $0.834 input, $2.501 output and $0.042 cached input.", + "input_cost_per_token": 4.17e-07, + "input_cost_per_token_cache_hit": 2.1e-08, + "litellm_provider": "tencent", + "max_input_tokens": 960000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.2505e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true + }, "tencent/minimax-m3": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 6e-08, @@ -59532,7 +64801,7 @@ "max_input_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://www.tencentcloud.com/products/tokenhub", + "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], @@ -59543,6 +64812,39 @@ "supports_reasoning": true, "supports_vision": false }, + "tencent/seedream-image-v5.0-flash": { + "litellm_provider": "tencent", + "mode": "image_generation", + "output_cost_per_image": 0.018, + "output_cost_per_image_token": 1.6e-06, + "source": "https://cloud.tencent.com/document/product/1823/130055", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ] + }, + "tencent/seedream-image-v5.0-lite": { + "litellm_provider": "tencent", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_image_token": 1.6e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ] + }, + "tencent/seedream-image-v5.0-pro": { + "litellm_provider": "tencent", + "mode": "image_generation", + "output_cost_per_image": 0.09, + "output_cost_per_image_token": 1.6e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ] + }, "cognition/swe-1.6": { "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06, @@ -59574,7 +64876,6 @@ "source": "https://docs.devin.ai/desktop/models" }, "pinstripes/ps/glm-4.5-air": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.25e-07, @@ -59587,7 +64888,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3.6-35b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.4e-07, @@ -59600,7 +64900,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3-30b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-08, @@ -59613,7 +64912,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3-coder-30b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-07, @@ -59626,7 +64924,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/deepseek-v4-flash": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1e-07, @@ -59639,7 +64936,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/minimax-m2.7": { - "max_tokens": 1000192, "max_input_tokens": 1000192, "max_output_tokens": 1000192, "input_cost_per_token": 2.55e-07, @@ -59656,7 +64952,6 @@ "litellm_provider": "darkbloom", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.65e-07, "source": "https://www.darkbloom.dev/", @@ -59673,7 +64968,6 @@ "litellm_provider": "darkbloom", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7e-08, "source": "https://www.darkbloom.dev/", @@ -59693,7 +64987,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -59720,7 +65013,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -59749,7 +65041,6 @@ "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.x.ai/v1/language-models", @@ -59768,6 +65059,10 @@ "input_cost_per_second": 7.5e-05, "litellm_provider": "openai", "mode": "audio_transcription", + "provider_specific_entry": { + "transcription_json_or_text_only": 1, + "transcription_usage_duration": 1 + }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/transcriptions", @@ -59780,7 +65075,8 @@ "supported_output_modalities": [ "text" ], - "supports_audio_input": true + "supports_audio_input": true, + "supports_native_streaming": true }, "gpt-live-transcribe": { "input_cost_per_second": 0.000283333333333, @@ -59798,7 +65094,8 @@ "supported_output_modalities": [ "text" ], - "supports_audio_input": true + "supports_audio_input": true, + "supports_native_streaming": true }, "gpt-live-1": { "input_cost_per_second": 0.000833333333333, @@ -59822,7 +65119,6 @@ "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, - "max_tokens": 2000, "mode": "realtime", "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ @@ -59833,7 +65129,8 @@ "audio" ], "supports_audio_input": true, - "supports_audio_output": true + "supports_audio_output": true, + "supports_native_streaming": true }, "claude-mythos-5": { "supports_anthropic_compaction": true, @@ -59847,7 +65144,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -59891,7 +65187,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -59924,8 +65219,56 @@ "supports_native_structured_output": true, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, + "claude-mythos-5-2": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "input_cost_per_token_batches": 4e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "output_cost_per_token_batches": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "fast": 2, + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_fast_mode": true, + "supports_speed": true + }, "claude-mythos-preview": { "deprecation_date": "2026-06-09", + "deprecation_source": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, @@ -59934,7 +65277,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "prompt_cache_min_tokens": 512, @@ -59970,7 +65312,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 5e-06, "search_context_cost_per_query": { @@ -60005,7 +65346,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "reasoning_effort_levels": [ @@ -60026,13 +65366,14 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/models/model-cards/leanstral-1-5", "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "mistral/mistral-moderation-2603": { "input_cost_per_token": 0.0, @@ -60043,6 +65384,7 @@ "source": "https://docs.mistral.ai/models/model-cards/mistral-moderation-26-03" }, "mistral/voxtral-mini-2602": { + "deprecation_date": "2027-04-30", "input_cost_per_second": 5e-05, "litellm_provider": "mistral", "mode": "audio_transcription", @@ -60059,6 +65401,7 @@ "supports_audio_input": true }, "mistral/voxtral-mini-transcribe-realtime-2602": { + "deprecation_date": "2027-04-30", "input_cost_per_second": 0.0001, "litellm_provider": "mistral", "mode": "audio_transcription", @@ -60075,6 +65418,7 @@ "supports_audio_input": true }, "mistral/voxtral-mini-tts-2603": { + "deprecation_date": "2027-04-30", "input_cost_per_character": 1.6e-05, "litellm_provider": "mistral", "mode": "audio_speech", @@ -60108,15 +65452,23 @@ "litellm_provider": "anthropic" } }, + { + "name": "typesafe-jev-ids", + "pattern": "^jev-(?:latest|preview|1\\.13\\.0|1\\.14\\.0)$", + "description": "A bare Jev id that has a typesafe/ price entry (jev-latest, jev-preview, jev-1.13.0, jev-1.14.0), the name the /typesafe pass-through forwards to TypeSafe. Listed by name, matched case-insensitively like every rule here, so foo/jev-latest or a model group named like a Jev id TypeSafe does not serve, such as jev-1.0 or jev-internal-router, never resolves to typesafe. A new Jev version goes here together with its price entry. Provider inference feeds the proxy's provider/* wildcard access checks, so this rule is what lets typesafe/* on a key, team or project allowlist cover a jev-latest request.", + "model_info": { + "litellm_provider": "typesafe" + } + }, { "name": "claude-family-baseline", "pattern": "claude-[a-z]+-\\d+(?:[-.]\\d+)?(?:-\\d{8})?", - "description": "Any Claude family-major id with an optional minor and an optional 8-digit date suffix, under any provider namespace (bare, bedrock-dotted, vertex, databricks, ...), so bare majors like claude-newfamily-5 get the same baseline as claude-newfamily-5-1. Carries the model-family facts every Claude shares; it carries no pricing, so cost stays on the standard unpriced behavior rather than a guessed number.", + "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "description": "Any Claude family-major id with an optional minor and an optional 8-digit date suffix, under any provider namespace (bare, bedrock-dotted, vertex, databricks, ...), so bare majors like claude-newfamily-5 get the same baseline as claude-newfamily-5-1. Carries the model-family facts every Claude shares; it carries no pricing, so cost stays on the standard unpriced behavior rather than a guessed number. On mapped Claude entries from Anthropic, Azure Foundry, Bedrock and Vertex it only fills the keys an entry leaves out, so the entry's own values always win.", "model_info": { "mode": "chat", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, @@ -60155,6 +65507,14 @@ "thinking_always_on": true } }, + { + "name": "claude-thinking-on-by-default", + "pattern": "claude-[a-z]+-[5-9](?!\\d)", + "description": "Claude at major 5 or higher, in any id shape that contains claude--. Anthropic's thinking docs list every Claude 5+ model as thinking by default (on or always on) when the request sends no thinking param, and every 4.x as off. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. The response_format json tool is then left unforced, since a forced tool call skips the model's thinking.", + "model_info": { + "thinking_on_by_default": true + } + }, { "name": "claude-mid-conversation-system", "pattern": "claude-[a-z]+-(?:4[-._](?:[89]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", @@ -60167,12 +65527,21 @@ { "name": "claude-tool-search", "pattern": "claude-[a-z]+-(?:4[-._](?:[5-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", - "fill_missing_for_providers": ["anthropic", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], - "description": "Claude at version 4.5 or higher, in any id shape that contains claude--: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is left out on purpose: Anthropic documents tool search as unavailable on Azure-hosted Foundry deployments, and the azure_ai/ key cannot tell those from Anthropic-hosted ones.", + "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "description": "Claude at version 4.5 or higher, in any id shape that contains claude--: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is included because Microsoft Foundry runs tool search for Claude on both Anthropic-hosted and Azure-hosted deployments.", "model_info": { "supports_tool_search": true } }, + { + "name": "claude-per-turn-control", + "pattern": "claude-[a-z]+-(?:4[-._](?:[5-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", + "fill_missing_for_providers": ["bedrock", "bedrock_converse"], + "description": "Claude at version 4.5 or higher, with the same id shapes and version boundaries as claude-tool-search. On 2026-11-05 Bedrock InvokeModel answered 200 with the per-turn-control-2026-07-01 beta on every Claude 4.5 and newer model a QA account reached across 13 regions, and 400 invalid beta flag on Claude 3 Haiku in ca-central-1. The jp., au. and in. profiles answered 200 too, AWS lists no apac. profile for Claude 4.5 or newer, and GovCloud was not tested. Claude 3.5, 3.7, Sonnet 4, Opus 4 and Opus 4.1 were unreachable, so they keep the beta dropped as before. The flag means Bedrock accepts the beta name on the model, as supports_tool_search does for the tool search beta, and Bedrock Invoke forwards the beta only where it is set. It does not promise per-turn output_config works, since on 2026-11-05 Opus 4.8, Opus 5, Sonnet 5 and Fable 5 rejected it with or without the beta. A deployment turns the forward off with model_info supports_per_turn_control false.", + "model_info": { + "supports_per_turn_control": true + } + }, { "name": "wandb-reasoning-baseline", "pattern": "^wandb/", @@ -60181,6 +65550,14 @@ "supports_reasoning": true } }, + { + "name": "minimax-reasoning-baseline", + "pattern": "^minimax/", + "description": "Any MiniMax model id under the minimax/ namespace, anchored so only that provider's ids match. MiniMax ships reasoning models faster than this registry names them, so an id the map has not described yet is treated as reasoning-capable and keeps the caller's reasoning_effort and thinking instead of dropping them. Rules lose to exact entries, so mapped speech, video and image models are unaffected. Carries no mode and no pricing, so cost stays on the standard unpriced behavior.", + "model_info": { + "supports_reasoning": true + } + }, { "name": "openai-reasoning-family-baseline", "pattern": "^(?!.*search-api)(?:[a-z0-9_.-]+/)*(?:ft:)?(?:o[1-9]\\d*(?![a-z0-9])|gpt-[5-9](?:\\.\\d+)?(?![0-9.])|(?:gpt-\\d+(?:\\.\\d+)?(?:-[a-z0-9]+)*-)?(?:codex|deep-research|chat-latest)(?![a-z0-9]))", @@ -60215,7 +65592,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 2.1e-05, "output_cost_per_token": 2.1e-05, @@ -60244,7 +65620,6 @@ "litellm_provider": "gemini", "max_input_tokens": 98304, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "audio_transcription", "output_cost_per_token": 1.2e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -60269,7 +65644,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "audio_transcription", "output_cost_per_token": 2.1e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -60350,7 +65724,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -60360,7 +65733,6 @@ "input_cost_per_token": 5e-08, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560, @@ -60370,7 +65742,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -60380,7 +65751,6 @@ "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -60390,7 +65760,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -60400,7 +65769,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -60410,7 +65778,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 120000, - "max_tokens": 120000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -60420,7 +65787,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -60436,7 +65802,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -60453,14 +65818,15 @@ "input_cost_per_token": 3e-07, "input_cost_per_token_priority": 3.75e-07, "litellm_provider": "fireworks_ai", + "token_count_framing": 23, "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.5e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60475,12 +65841,12 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.8e-06, "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60495,7 +65861,7 @@ "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -60513,7 +65879,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_priority": 1.875e-05, @@ -60524,11 +65889,39 @@ ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/kimi-latest": { + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_priority": 3.75e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_priority": 3.75e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_priority": 1.875e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/kimi-latest": { + "alias_of": "fireworks_ai/accounts/fireworks/models/kimi-k3" + }, "fireworks_ai/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 7e-09, "cache_read_input_token_cost_priority": 8.75e-09, @@ -60538,7 +65931,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -60555,14 +65947,15 @@ "input_cost_per_token": 3e-07, "input_cost_per_token_priority": 3.75e-07, "litellm_provider": "fireworks_ai", + "token_count_framing": 23, "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.5e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60577,12 +65970,12 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.8e-06, "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60597,7 +65990,7 @@ "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -60610,14 +66003,15 @@ "fireworks_ai/glm-5p2-fast": { "cache_read_input_token_cost": 2.1e-07, "deprecation_date": "2026-09-25", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/glm-5p3", "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60627,14 +66021,15 @@ "fireworks_ai/glm-5p2-fast-us": { "cache_read_input_token_cost": 2.1e-07, "deprecation_date": "2026-09-25", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/glm-5p3", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60649,7 +66044,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_priority": 1.875e-05, @@ -60660,6 +66054,7 @@ ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -60671,7 +66066,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "reasoning_effort_levels": [ @@ -60681,6 +66075,7 @@ ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -60694,7 +66089,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "output_cost_per_token_priority": 2.8125e-05, @@ -60705,6 +66099,7 @@ ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -60722,6 +66117,7 @@ "output_cost_per_token_priority": 9e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -60736,7 +66132,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "output_cost_per_token_priority": 2.25e-06, @@ -60750,16 +66145,18 @@ "fireworks_ai/nemotron-lightning-3p5-30b-a3b": { "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_priority": 1.25e-08, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 5e-08, "input_cost_per_token_priority": 6.25e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "output_cost_per_token_priority": 2.5e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "successor_model": "Nemotron Super VL", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60769,17 +66166,20 @@ "fireworks_ai/nemotron-3-ultra-nvfp4": { "cache_read_input_token_cost": 1.2e-07, "cache_read_input_token_cost_priority": 1.5e-07, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 6e-07, "input_cost_per_token_priority": 7.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-06, "output_cost_per_token_priority": 3e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "successor_model": "Nemotron Super VL", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -60794,7 +66194,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "output_cost_per_token_priority": 2.25e-06, @@ -60805,19 +66204,38 @@ "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/accounts/fireworks/models/muse-spark-open": { + "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_priority": 2.25e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_priority": 1.875e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "output_cost_per_token_priority": 6.375e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, "fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": { "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_priority": 1.25e-08, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 5e-08, "input_cost_per_token_priority": 6.25e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "output_cost_per_token_priority": 2.5e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "successor_model": "Nemotron Super VL", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60827,17 +66245,20 @@ "fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4": { "cache_read_input_token_cost": 1.2e-07, "cache_read_input_token_cost_priority": 1.5e-07, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 6e-07, "input_cost_per_token_priority": 7.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-06, "output_cost_per_token_priority": 3e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "successor_model": "Nemotron Super VL", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -60853,8 +66274,27 @@ "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_priority": 9e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, + "supports_mid_conversation_system": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/qwen-max-latest": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_priority": 3.75e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_priority": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_priority": 9e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -60863,14 +66303,15 @@ "fireworks_ai/accounts/fireworks/routers/glm-5p2-fast": { "cache_read_input_token_cost": 2.1e-07, "deprecation_date": "2026-09-25", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/accounts/fireworks/models/glm-5p3", "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60880,14 +66321,15 @@ "fireworks_ai/accounts/fireworks/routers/glm-5p2-fast-us": { "cache_read_input_token_cost": 2.1e-07, "deprecation_date": "2026-09-25", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/accounts/fireworks/models/glm-5p3", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60900,7 +66342,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "reasoning_effort_levels": [ @@ -60910,6 +66351,28 @@ ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/kimi-fast-latest": { + "cache_read_input_token_cost": 4.5e-07, + "input_cost_per_token": 4.5e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.25e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -60923,7 +66386,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "output_cost_per_token_priority": 2.8125e-05, @@ -60934,6 +66396,7 @@ ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -60945,7 +66408,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -60957,12 +66419,11 @@ "supports_vision": false }, "novita/deepseek/deepseek-v4-pro-0813": { - "cache_read_input_token_cost": 1.3200000000000002e-07, + "cache_read_input_token_cost": 4.4e-08, "input_cost_per_token": 1.32e-06, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://novita.ai/pricing", @@ -60979,7 +66440,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://novita.ai/pricing", @@ -60996,7 +66456,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 5.8e-07, "source": "https://novita.ai/pricing", @@ -61013,7 +66472,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://novita.ai/pricing", @@ -61030,7 +66488,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://novita.ai/pricing", @@ -61047,7 +66504,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -61064,7 +66520,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://novita.ai/pricing", @@ -61076,14 +66531,13 @@ "supports_vision": false }, "novita/mindai/macaron-v1-venti": { - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 1.5e-06, + "cache_read_input_token_cost": 1.65e-07, + "input_cost_per_token": 8.25e-07, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4.5e-06, + "output_cost_per_token": 2.475e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, @@ -61097,7 +66551,6 @@ "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", @@ -61114,7 +66567,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://novita.ai/pricing", @@ -61131,7 +66583,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", @@ -61148,7 +66599,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://novita.ai/pricing", @@ -61164,7 +66614,6 @@ "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://novita.ai/pricing", @@ -61181,7 +66630,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://novita.ai/pricing", @@ -61192,14 +66640,13 @@ "supports_vision": false }, "novita/mindai/macaron-v1-tall": { - "cache_read_input_token_cost": 8e-08, - "input_cost_per_token": 4.5000000000000003e-07, + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 2.475e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2.6e-06, + "output_cost_per_token": 1.43e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, @@ -61213,7 +66660,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://novita.ai/pricing", @@ -61229,7 +66675,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.0000000000000002e-07, "source": "https://novita.ai/pricing", @@ -61245,7 +66690,6 @@ "litellm_provider": "novita", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.13e-06, "source": "https://novita.ai/pricing", @@ -61261,7 +66705,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.3600000000000004e-07, "source": "https://novita.ai/pricing", @@ -61278,7 +66721,6 @@ "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.75e-06, "source": "https://novita.ai/pricing", @@ -61295,7 +66737,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.044e-06, "source": "https://novita.ai/pricing", @@ -61311,7 +66752,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.6000000000000003e-06, "source": "https://novita.ai/pricing", @@ -61327,7 +66767,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.4e-06, "source": "https://novita.ai/pricing", @@ -61344,7 +66783,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://novita.ai/pricing", @@ -61361,7 +66799,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -61378,7 +66815,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -61394,7 +66830,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", @@ -61409,7 +66844,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", @@ -61425,7 +66859,6 @@ "litellm_provider": "novita", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -61442,7 +66875,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", @@ -61459,7 +66891,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131100, - "max_tokens": 131100, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://novita.ai/pricing", @@ -61475,7 +66906,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://novita.ai/pricing", @@ -61490,7 +66920,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", @@ -61505,7 +66934,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://novita.ai/pricing", @@ -61520,7 +66948,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.6000000000000003e-06, "source": "https://novita.ai/pricing", @@ -61536,7 +66963,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131100, - "max_tokens": 131100, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", @@ -61553,7 +66979,6 @@ "litellm_provider": "novita", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", @@ -61569,7 +66994,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://novita.ai/pricing", @@ -61583,7 +67007,6 @@ "litellm_provider": "novita", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://novita.ai/pricing", @@ -61595,7 +67018,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://novita.ai/pricing", @@ -61612,7 +67034,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -61629,7 +67050,6 @@ "litellm_provider": "novita", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", @@ -61645,7 +67065,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.4850000000000002e-06, "source": "https://novita.ai/pricing", @@ -61660,7 +67079,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 8.900000000000001e-07, "source": "https://api.novita.ai/v3/openai/models", @@ -61673,7 +67091,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -61687,7 +67104,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8.900000000000001e-07, "source": "https://api.novita.ai/v3/openai/models", @@ -61700,7 +67116,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -61714,7 +67129,6 @@ "litellm_provider": "novita", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.66e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -61728,7 +67142,6 @@ "litellm_provider": "novita", "max_input_tokens": 131000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2e-08, "source": "https://api.novita.ai/v3/openai/models", @@ -61737,7 +67150,7 @@ }, "wandb/deepseek-ai/DeepSeek-V4-Flash": { "supports_reasoning": true, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1049000, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, @@ -61751,20 +67164,20 @@ }, "wandb/deepseek-ai/DeepSeek-V4-Flash-0731": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 2.8e-07, - "cache_read_input_token_cost": 7e-08, + "output_cost_per_token": 2.7e-07, + "cache_read_input_token_cost": 5e-08, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, - "source": "https://wandb.ai/site/pricing/tokens/" + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "wandb/deepseek-ai/DeepSeek-V4-Pro": { "supports_reasoning": true, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1049000, "input_cost_per_token": 1.15e-06, "output_cost_per_token": 2.55e-06, @@ -61778,7 +67191,7 @@ }, "wandb/google/gemma-4-31B-it": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3.4e-07, @@ -61789,7 +67202,7 @@ }, "wandb/ibm-granite/granite-4.1-8b": { "deprecation_date": "2026-10-05", - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131000, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, @@ -61800,7 +67213,7 @@ }, "wandb/JetBrains/Mellum2-12B-A2.5B-Instruct": { "deprecation_date": "2026-10-05", - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131000, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, @@ -61811,7 +67224,7 @@ }, "wandb/meta-llama/Llama-3.1-70B-Instruct": { "deprecation_date": "2026-10-05", - "max_tokens": 128000, + "max_output_tokens": 128000, "max_input_tokens": 131000, "input_cost_per_token": 8e-07, "output_cost_per_token": 8e-07, @@ -61822,7 +67235,7 @@ }, "wandb/MiniMaxAI/MiniMax-M3": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 2.3e-07, "output_cost_per_token": 9.6e-07, @@ -61835,20 +67248,20 @@ }, "wandb/moonshotai/Kimi-K2.7-Code": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, - "input_cost_per_token": 7.1e-07, - "output_cost_per_token": 3.5e-06, - "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 1.2e-07, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": true, - "source": "https://wandb.ai/site/pricing/tokens/" + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "wandb/moonshotai/Kimi-K2.6": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 6.5e-07, "output_cost_per_token": 3.41e-06, @@ -61861,7 +67274,7 @@ }, "wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 7e-08, "output_cost_per_token": 2e-07, @@ -61874,7 +67287,7 @@ }, "wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.15e-06, @@ -61887,7 +67300,7 @@ }, "wandb/OpenPipe/Qwen3-14B-Instruct": { "deprecation_date": "2026-10-05", - "max_tokens": 32768, + "max_output_tokens": 32768, "max_input_tokens": 32800, "input_cost_per_token": 5e-08, "output_cost_per_token": 2.2e-07, @@ -61898,7 +67311,7 @@ }, "wandb/Qwen/Qwen3.8-27B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 4e-07, "output_cost_per_token": 3e-06, @@ -61910,19 +67323,21 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3.6-35B-A3B": { + "cache_read_input_token_cost": 3.5e-08, "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 8.9e-07, "litellm_provider": "wandb", "mode": "chat", "supports_vision": true, - "source": "https://wandb.ai/site/pricing/tokens/" + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", + "supports_prompt_caching": true }, "wandb/Qwen/Qwen3.6-27B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 6e-07, "output_cost_per_token": 3.6e-06, @@ -61937,7 +67352,7 @@ "wandb/Qwen/Qwen3.5-35B-A3B": { "deprecation_date": "2026-10-05", "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.25e-06, @@ -61948,7 +67363,7 @@ }, "wandb/Qwen/Qwen3-30B-A3B-Instruct-2507": { "deprecation_date": "2026-10-05", - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, @@ -61972,28 +67387,28 @@ "litellm_provider": "wandb", "mode": "chat", "supports_reasoning": true, - "input_cost_per_token": 1e-07, + "input_cost_per_token": 6e-08, "output_cost_per_token": 1.5e-07, - "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost": 1.5e-08, "max_input_tokens": 131000, "supports_prompt_caching": true, - "source": "https://wandb.ai/site/pricing/tokens/" + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "wandb/zai-org/GLM-5.2": { "supports_reasoning": true, - "max_tokens": 262144, - "max_input_tokens": 1049000, - "input_cost_per_token": 7.6e-07, + "max_output_tokens": 262144, + "max_input_tokens": 262000, + "input_cost_per_token": 6.2e-07, "output_cost_per_token": 2.42e-06, "cache_read_input_token_cost": 1.4e-07, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, - "source": "https://wandb.ai/site/pricing/tokens/" + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "deepinfra/openai/gpt-oss-120b-Turbo": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, @@ -62007,7 +67422,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M2.7": { - "max_tokens": 196608, + "max_output_tokens": 196608, "max_input_tokens": 196608, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1e-06, @@ -62023,7 +67438,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-27B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4e-07, "output_cost_per_token": 3e-06, @@ -62039,7 +67454,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it-Ultra": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2.7e-07, "output_cost_per_token": 7.6e-07, @@ -62053,7 +67468,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.5": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 2.25e-06, @@ -62069,7 +67484,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.7-Flash": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 6e-08, "output_cost_per_token": 4e-07, @@ -62085,7 +67500,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.6": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 5e-07, "output_cost_per_token": 2e-06, @@ -62104,7 +67519,7 @@ "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 1024, @@ -62118,7 +67533,7 @@ "supports_vision": true }, "deepinfra/anthropic/claude-sonnet-4-6": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, @@ -62134,7 +67549,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.5-flash": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 1.5e-06, "output_cost_per_token": 9e-06, @@ -62149,7 +67564,7 @@ "supports_audio_input": true }, "deepinfra/XiaomiMiMo/MiMo-V2.5": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4e-07, "output_cost_per_token": 2e-06, @@ -62165,7 +67580,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Max": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, @@ -62180,7 +67595,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it-turbo": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 9e-08, "output_cost_per_token": 3.4e-07, @@ -62195,7 +67610,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/thinkingmachines/Inkling-Small": { - "max_tokens": 524288, + "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 1.2e-06, @@ -62211,7 +67626,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-models/Muse-Glimmer-30B": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, @@ -62227,7 +67642,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Max-Thinking": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, @@ -62242,7 +67657,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-07, "output_cost_per_token": 8.8e-07, @@ -62257,7 +67672,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, @@ -62270,7 +67685,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-27B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2.6e-07, "output_cost_per_token": 2.6e-06, @@ -62284,7 +67699,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.6-35B-A3B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1e-07, "output_cost_per_token": 9.5e-07, @@ -62298,7 +67713,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/Nemotron-Content-Safety-3.5": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -62311,7 +67726,7 @@ "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 512, @@ -62325,7 +67740,7 @@ "supports_vision": true }, "deepinfra/thinkingmachines/Inkling": { - "max_tokens": 524288, + "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 9.5e-07, "output_cost_per_token": 4.05e-06, @@ -62341,7 +67756,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.6": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 3.5e-06, @@ -62357,7 +67772,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1.3e-06, "output_cost_per_token": 2.6e-06, @@ -62372,7 +67787,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.7-Max": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 2.5e-06, "output_cost_per_token": 7.5e-06, @@ -62387,7 +67802,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-mini": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1e-07, "output_cost_per_token": 4e-07, @@ -62403,7 +67818,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-2.4T-A95B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, @@ -62419,7 +67834,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M3": { - "max_tokens": 524288, + "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 2.8e-07, "output_cost_per_token": 1.1e-06, @@ -62435,7 +67850,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.1-flash-lite": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.5e-06, @@ -62450,7 +67865,7 @@ "supports_audio_input": true }, "deepinfra/google/gemini-3.7-flash": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 3.75e-06, @@ -62460,12 +67875,13 @@ "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_vision": true, "source": "https://deepinfra.com/pricing", "supports_audio_input": true }, "deepinfra/inclusionAI/Ling-3.0-flash": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 6e-08, "output_cost_per_token": 1.8e-07, @@ -62481,7 +67897,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/stepfun-ai/Step-3.7-Flash": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-07, "output_cost_per_token": 1.15e-06, @@ -62495,7 +67911,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-35B-A3B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 1e-06, @@ -62511,7 +67927,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-1.8": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, @@ -62527,7 +67943,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/tencent/Hy3": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 5.8e-07, @@ -62543,7 +67959,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-code": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, @@ -62559,7 +67975,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-pro": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, @@ -62575,7 +67991,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 6e-07, "output_cost_per_token": 2.08e-06, @@ -62591,7 +68007,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/Nemotron-3-Nano-30B-A3B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 5e-08, "output_cost_per_token": 2e-07, @@ -62606,7 +68022,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.7-Code": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 6.8e-07, "output_cost_per_token": 3.4e-06, @@ -62622,12 +68038,12 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-sonnet-5": { - "input_cost_per_token": 2e-06, + "input_cost_per_token": 3e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 1e-05, + "output_cost_per_token": 1.5e-05, "prompt_cache_min_tokens": 1024, "source": "https://deepinfra.com/pricing", "supports_adaptive_thinking": true, @@ -62639,7 +68055,7 @@ "supports_vision": true }, "deepinfra/Qwen/Qwen3.5-397B-A17B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 3e-06, @@ -62655,11 +68071,11 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, - "input_cost_per_token": 8e-08, + "input_cost_per_token": 6e-08, "output_cost_per_token": 1.8e-07, - "cache_read_input_token_cost": 1.6e-08, + "cache_read_input_token_cost": 1.5e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", @@ -62671,7 +68087,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-E4B-it": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-08, "output_cost_per_token": 1e-07, @@ -62684,7 +68100,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.2": { - "max_tokens": 163840, + "max_output_tokens": 163840, "max_input_tokens": 163840, "input_cost_per_token": 2.6e-07, "output_cost_per_token": 3.8e-07, @@ -62699,7 +68115,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-Max": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.65e-06, "output_cost_per_token": 4.951e-06, @@ -62717,7 +68133,7 @@ "input_cost_per_token": 1e-05, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 5e-05, "prompt_cache_min_tokens": 512, @@ -62732,7 +68148,7 @@ "thinking_always_on": true }, "deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.2e-06, @@ -62748,7 +68164,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-122B-A10B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2.9e-07, "output_cost_per_token": 2.4e-06, @@ -62762,7 +68178,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5.1": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 1.05e-06, "output_cost_per_token": 3.5e-06, @@ -62778,7 +68194,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Pro": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1.3e-06, "output_cost_per_token": 2.6e-06, @@ -62793,9 +68209,9 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, - "input_cost_per_token": 8.5e-08, + "input_cost_per_token": 7.5e-08, "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", @@ -62807,7 +68223,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5.2": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 2.4e-06, @@ -62823,7 +68239,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K3": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 2.85e-06, "output_cost_per_token": 1.425e-05, @@ -62841,7 +68257,7 @@ "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 2048, @@ -62855,7 +68271,7 @@ "supports_vision": true }, "deepinfra/Qwen/Qwen3.6-27B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 3.2e-07, "output_cost_per_token": 3.2e-06, @@ -62869,7 +68285,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-26B-A4B-it": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 7e-08, "output_cost_per_token": 3.4e-07, @@ -62883,7 +68299,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.1-pro": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 2e-06, "output_cost_per_token": 1.2e-05, @@ -62898,7 +68314,7 @@ "supports_audio_input": true }, "deepinfra/XiaomiMiMo/MiMo-V2.5-Pro": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1e-06, "output_cost_per_token": 3e-06, @@ -62914,7 +68330,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-haiku-4-5": { - "max_tokens": 200000, + "max_output_tokens": 200000, "max_input_tokens": 200000, "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, @@ -62929,7 +68345,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Flash": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 9e-08, "output_cost_per_token": 1.8e-07, @@ -62944,8 +68360,40 @@ "supports_vision": false, "source": "https://deepinfra.com/pricing" }, + "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 4.2e-07, + "cache_read_input_token_cost": 4.2e-09, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash" + }, + "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 4.2e-07, + "cache_read_input_token_cost": 4.2e-09, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash-1017" + }, "deepinfra/openai/gpt-oss-120b-Ultra": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 9.5e-07, @@ -62959,7 +68407,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-9B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1e-07, "output_cost_per_token": 1.5e-07, @@ -62972,7 +68420,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo": { - "max_tokens": 196608, + "max_output_tokens": 196608, "max_input_tokens": 196608, "input_cost_per_token": 3.8e-07, "output_cost_per_token": 1.7e-06, @@ -62988,7 +68436,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.7": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 4e-07, "output_cost_per_token": 1.75e-06, @@ -63004,10 +68452,10 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 3.8e-07, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, @@ -63018,18 +68466,20 @@ "source": "https://deepinfra.com/pricing" }, "gemini/gemini-omni-1.1-flash": { + "deprecation_date": "2026-12-03", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/models/gemini-omni-flash", + "successor_model": "gemini/gemini-omni-1.2-flash", "supported_endpoints": [ "/v1beta/interactions" ], @@ -63058,7 +68508,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -63086,7 +68535,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -63114,7 +68562,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -63168,10 +68615,14 @@ }, "xai/grok-imagine-image-quality": { "deprecation_date": "2026-11-02", - "input_cost_per_image": 0.05, + "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", + "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", + "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" ], @@ -63185,10 +68636,14 @@ }, "xai/grok-imagine-image-quality-20260403": { "deprecation_date": "2026-11-02", - "input_cost_per_image": 0.05, + "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", + "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", + "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" ], @@ -63202,10 +68657,14 @@ }, "xai/grok-imagine-image-quality-latest": { "deprecation_date": "2026-11-02", - "input_cost_per_image": 0.05, + "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", + "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", + "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" ], @@ -63218,10 +68677,15 @@ ] }, "xai/grok-imagine-image-pro": { - "input_cost_per_image": 0.05, + "deprecation_date": "2026-05-15", + "deprecation_source": "https://docs.x.ai/developers/migration/may-15-retirement", + "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", + "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" ], @@ -63237,7 +68701,9 @@ "input_cost_per_image": 0.06, "litellm_provider": "xai", "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "supported_endpoints": [ "/v1/images/generations" ], @@ -63339,6 +68805,8 @@ }, "xai/grok-voice-transcribe-1.0": { "deprecation_date": "2026-10-02", + "deprecation_source": "https://docs.x.ai/docs/release-notes", + "successor_model": "xai/grok-voice-transcribe-2.0", "input_cost_per_second": 2.778e-05, "litellm_provider": "xai", "metadata": { @@ -63390,7 +68858,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -63417,7 +68884,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -63444,7 +68910,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -63475,7 +68940,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -63503,7 +68967,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://console.groq.com/docs/model/qwen/qwen3.8-27b", @@ -63519,7 +68982,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -63540,7 +69002,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -63561,7 +69022,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -63582,7 +69042,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "reasoning_effort_levels": [ @@ -63603,7 +69062,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", @@ -63618,7 +69076,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", @@ -63633,12 +69090,16 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://mistral.ai/news/devstral-2-vibe-cli", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, @@ -63734,13 +69195,14 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/models/model-cards/leanstral-1-5", "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/glm-5p3": { "cache_read_input_token_cost": 2.6e-07, @@ -63750,12 +69212,31 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/routers/glm-latest": { + "cache_read_input_token_cost": 2.6e-07, + "cache_read_input_token_cost_priority": 3.25e-07, + "input_cost_per_token": 1.4e-06, + "input_cost_per_token_priority": 1.75e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "output_cost_per_token_priority": 5.5e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -63769,12 +69250,12 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.6e-06, "output_cost_per_token_priority": 8.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -63788,12 +69269,12 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -63807,12 +69288,12 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.6e-06, "output_cost_per_token_priority": 8.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -63823,11 +69304,28 @@ "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/routers/glm-fast-latest": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -63865,11 +69363,12 @@ "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -63882,12 +69381,31 @@ "input_cost_per_token_priority": 1.875e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_priority": 6.25e-07, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/glm-flash-latest": { + "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_priority": 3.75e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_priority": 1.875e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_priority": 6.25e-07, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -63895,16 +69413,20 @@ "fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us": { "cache_read_input_token_cost": 4.5e-08, "cache_read_input_token_cost_priority": 5.625e-08, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2.25e-07, "input_cost_per_token_priority": 2.8125e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-07, "output_cost_per_token_priority": 9.375e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -63916,12 +69438,13 @@ "input_cost_per_token_priority": 1.875e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_priority": 6.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -63929,16 +69452,20 @@ "fireworks_ai/glm-5p3-flash-us": { "cache_read_input_token_cost": 4.5e-08, "cache_read_input_token_cost_priority": 5.625e-08, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2.25e-07, "input_cost_per_token_priority": 2.8125e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-07, "output_cost_per_token_priority": 9.375e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://docs.fireworks.ai/changelog.md", + "successor_model": "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -63946,16 +69473,20 @@ "fireworks_ai/accounts/fireworks/models/inkling": { "cache_read_input_token_cost": 1.7e-07, "cache_read_input_token_cost_priority": 1.7e-07, + "deprecation_date": "2026-11-07", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1e-06, "input_cost_per_token_priority": 1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.05e-06, "output_cost_per_token_priority": 4.05e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "successor_model": "fireworks_ai/accounts/fireworks/models/muse-spark-open", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -63966,9 +69497,8 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 40960, "max_output_tokens": 40960, - "max_tokens": 40960, "mode": "embedding", - "source": "https://api.fireworks.ai/v1/serverless/models" + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested" }, "zai/glm-5.2": { "cache_creation_input_token_cost": 0, @@ -63985,15 +69515,192 @@ "supports_reasoning": true, "supports_tool_choice": true }, + "zerogpu/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/glm-5.3-flash": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3.5e-07, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/gpt-5.4-nano": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/gpt-5.6-luna": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/gpt-6-luna": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "zerogpu/gpt-oss-120b": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/LFM2.5-1.2B-Instruct": { + "input_cost_per_token": 2e-08, + "litellm_provider": "zerogpu", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-08, + "source": "https://docs.zerogpu.ai/docs/model-catalog" + }, + "zerogpu/LFM2.5-1.2B-Thinking": { + "input_cost_per_token": 2e-08, + "litellm_provider": "zerogpu", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-08, + "source": "https://docs.zerogpu.ai/docs/model-catalog" + }, + "zerogpu/llama-3.1-8b-instruct-fast": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/llama-3.2-3b-instruct-fast": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 5e-08, + "litellm_provider": "zerogpu", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://docs.zerogpu.ai/docs/model-catalog" + }, + "zerogpu/qwen3-30b-a3b-fp8": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 4.5e-07, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "zerogpu/qwen3.6-35b-a3b": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-07, + "litellm_provider": "zerogpu", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.zerogpu.ai/docs/model-catalog", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "together_ai/Qwen/Qwen3.8-Flash": { "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://api.together.ai/v1/models" }, + "together_ai/qwen-flash-latest": { + "alias_of": "together_ai/Qwen/Qwen3.8-Flash" + }, "together_ai/moonshotai/Kimi-K2.5-fp4": { "input_cost_per_token": 5e-07, "output_cost_per_token": 2.8e-06, @@ -64029,6 +69736,7 @@ }, "together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { "deprecation_date": "2026-02-25", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 6e-08, "output_cost_per_token": 2.5e-07, "litellm_provider": "together_ai", @@ -64049,7 +69757,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 131072, "max_output_tokens": 40960, - "max_tokens": 40960, "mode": "chat", "output_cost_per_token": 1.49e-06, "source": "https://api.cerebras.ai/public/v1/models/gemma-4-31b", @@ -64071,11 +69778,11 @@ ] }, "scaleway/glm-5.2": { + "deprecation_date": "2026-11-16", "input_cost_per_token": 1.8e-06, "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://www.scaleway.com/en/pricing/model-as-a-service/", @@ -64089,7 +69796,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://www.scaleway.com/en/pricing/model-as-a-service/", @@ -64101,11 +69807,11 @@ "azure_ai/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, "deprecation_date": "2027-04-16", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 9.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -64117,25 +69823,39 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, + "azure_ai/deepseek-v4.1-flash-1017": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 6e-09, + "litellm_provider": "azure_ai", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "supports_prompt_caching": true, + "supports_vision": false, + "source": "https://ai.azure.com/catalog/models/DeepSeek-V4.1-Flash-1017" + }, "azure_ai/deepseek-v4.1-flash": { "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "deprecation_date": "2026-12-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/deepseek-v4-1-flash-is-coming-to-microsoft-foundry/4556431" }, "azure_ai/MAI-Image-2.6": { @@ -64170,11 +69890,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -64185,11 +69905,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.1e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -64200,30 +69920,36 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, + "azure_ai/glm-latest": { + "alias_of": "azure_ai/FW-GLM-5.3" + }, "azure_ai/FW-GLM-5.3-Flash": { "cache_read_input_token_cost": 3.8e-08, "input_cost_per_token": 1.88e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.25e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, + "azure_ai/glm-flash-latest": { + "alias_of": "azure_ai/FW-GLM-5.3-Flash" + }, "azure_ai/FW-GPT-OSS-120B": { "deprecation_date": "2027-07-01", "cache_read_input_token_cost": 8.2e-08, @@ -64231,12 +69957,12 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64244,15 +69970,17 @@ }, "azure_ai/Cohere-command-a-plus-05-2026": { "deprecation_date": "2026-10-16", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "coherelabs-command-a-plus-05-2026-fp81", "input_cost_per_token": 8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true }, @@ -64261,7 +69989,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -64272,74 +69999,101 @@ "supported_output_modalities": [ "text" ], + "supports_pdf_input": false, "supports_response_schema": true, "supports_vision": true }, "azure_ai/deepseek-r1": { "deprecation_date": "2026-08-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/deepseek-v4-pro", "input_cost_per_token": 1.35e-06, "output_cost_per_token": 5.4e-06, "litellm_provider": "azure_ai", "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false }, "azure_ai/deepseek-v3-0324": { "deprecation_date": "2026-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/deepseek-v4-flash", "input_cost_per_token": 1.14e-06, "output_cost_per_token": 4.56e-06, "litellm_provider": "azure_ai", "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false }, "azure_ai/deepseek-v3.1": { "deprecation_date": "2026-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/deepseek-v4-flash", "input_cost_per_token": 1.23e-06, "output_cost_per_token": 4.94e-06, "litellm_provider": "azure_ai", "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false }, "azure_ai/grok-3": { "deprecation_date": "2026-05-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/grok-4", "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "litellm_provider": "azure_ai", "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false }, "azure_ai/grok-3-mini": { "deprecation_date": "2026-05-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/grok-4-1-fast-reasoning", "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.27e-06, "litellm_provider": "azure_ai", "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false }, "azure_ai/grok-4-fast-non-reasoning": { "deprecation_date": "2026-05-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/grok-4-1-fast-non-reasoning", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false }, "azure_ai/grok-4-fast-reasoning": { "deprecation_date": "2026-05-01", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "successor_model": "azure_ai/grok-4-1-fast-reasoning", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", "mode": "chat", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_pdf_input": false }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 5.04e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -64350,14 +70104,20 @@ }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-12b-v2": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "input_cost_per_token_flex": 1.2e-07, + "input_cost_per_token_priority": 4.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_system_messages": true, "supports_vision": true, "supports_audio_input": false, @@ -64366,14 +70126,20 @@ }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-9b-v2": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 4.8e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_system_messages": true, "supports_audio_input": false, "supports_function_calling": true, @@ -64382,13 +70148,18 @@ }, "bedrock/us-gov-west-1/nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3.9e-07, + "output_cost_per_token_flex": 3.9e-07, + "output_cost_per_token_priority": 1.365e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -64398,14 +70169,20 @@ "supports_vision": false }, "bedrock/us-gov-west-1/openai.gpt-oss-20b-1:0": { + "supports_vision": false, "input_cost_per_token": 8.4e-08, + "input_cost_per_token_batches": 4.2e-08, + "input_cost_per_token_flex": 4.2e-08, + "input_cost_per_token_priority": 1.47e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", + "output_cost_per_token_batches": 1.8e-07, + "output_cost_per_token_flex": 1.8e-07, + "output_cost_per_token_priority": 6.3e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], @@ -64417,14 +70194,20 @@ "supports_tool_choice": true }, "bedrock/us-gov-west-1/openai.gpt-oss-120b-1:0": { + "supports_vision": false, "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], @@ -64446,17 +70229,18 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64466,7 +70250,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-west-1/anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -64479,7 +70268,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, @@ -64490,6 +70278,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64499,7 +70288,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-west-1/anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -64511,11 +70305,11 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -64531,7 +70325,15 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + }, + "input_cost_per_token_batches": 3e-06, + "output_cost_per_token_batches": 1.5e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json" }, "bedrock/us-gov-west-1/anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -64543,7 +70345,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.4e-05, "prompt_cache_min_tokens": 512, @@ -64554,6 +70355,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64566,7 +70368,12 @@ "supports_xhigh_reasoning_effort": true, "thinking_always_on": true, "supports_forced_tool_use": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-west-1/anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.5e-05, @@ -64576,7 +70383,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, @@ -64595,21 +70401,66 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "token_count_model": { + "model": "anthropic.claude-fable-5-1", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } + }, + "bedrock/us-gov-west-1/anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 5.04e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -64620,14 +70471,20 @@ }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "input_cost_per_token_flex": 1.2e-07, + "input_cost_per_token_priority": 4.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_system_messages": true, "supports_vision": true, "supports_audio_input": false, @@ -64636,14 +70493,20 @@ }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-9b-v2": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 4.8e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_system_messages": true, "supports_audio_input": false, "supports_function_calling": true, @@ -64652,13 +70515,18 @@ }, "bedrock/us-gov-east-1/nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3.9e-07, + "output_cost_per_token_flex": 3.9e-07, + "output_cost_per_token_priority": 1.365e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -64668,14 +70536,20 @@ "supports_vision": false }, "bedrock/us-gov-east-1/openai.gpt-oss-20b-1:0": { + "supports_vision": false, "input_cost_per_token": 8.4e-08, + "input_cost_per_token_batches": 4.2e-08, + "input_cost_per_token_flex": 4.2e-08, + "input_cost_per_token_priority": 1.47e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", + "output_cost_per_token_batches": 1.8e-07, + "output_cost_per_token_flex": 1.8e-07, + "output_cost_per_token_priority": 6.3e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], @@ -64687,14 +70561,20 @@ "supports_tool_choice": true }, "bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0": { + "supports_vision": false, "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], @@ -64716,17 +70596,18 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64749,7 +70630,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, @@ -64760,6 +70640,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64781,11 +70662,11 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -64801,7 +70682,10 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "input_cost_per_token_batches": 3e-06, + "output_cost_per_token_batches": 1.5e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-east-1/index.json" }, "bedrock/us-gov-east-1/anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -64813,7 +70697,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.4e-05, "prompt_cache_min_tokens": 512, @@ -64824,6 +70707,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64846,7 +70730,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, @@ -64865,17 +70748,51 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512 }, + "bedrock/us-gov-east-1/anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra": { "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -64897,21 +70814,38 @@ "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "input_cost_per_token": 2.7e-06, - "input_cost_per_token_above_272k_tokens": 5.4e-06, - "cache_creation_input_token_cost": 3.375e-06, - "cache_creation_input_token_cost_above_272k_tokens": 6.75e-06, - "cache_read_input_token_cost": 2.7e-07, - "cache_read_input_token_cost_above_272k_tokens": 5.4e-07, - "output_cost_per_token": 1.62e-05, - "output_cost_per_token_above_272k_tokens": 2.43e-05, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html" + "input_cost_per_token": 2.64e-06, + "input_cost_per_token_above_272k_tokens": 5.28e-06, + "cache_creation_input_token_cost": 3.3e-06, + "cache_creation_input_token_cost_above_272k_tokens": 6.6e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 3.3e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.32e-05, + "cache_creation_input_token_cost_flex": 1.65e-06, + "cache_creation_input_token_cost_priority": 6.6e-06, + "cache_read_input_token_cost": 2.64e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.28e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.64e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.056e-06, + "cache_read_input_token_cost_flex": 1.32e-07, + "cache_read_input_token_cost_priority": 5.28e-07, + "input_cost_per_token_above_272k_tokens_flex": 2.64e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.056e-05, + "input_cost_per_token_flex": 1.32e-06, + "input_cost_per_token_priority": 5.28e-06, + "output_cost_per_token": 1.584e-05, + "output_cost_per_token_above_272k_tokens": 2.376e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.188e-05, + "output_cost_per_token_above_272k_tokens_priority": 4.752e-05, + "output_cost_per_token_flex": 7.92e-06, + "output_cost_per_token_priority": 3.168e-05, + "search_context_cost_per_query": {"search_context_size_high":0.0144,"search_context_size_low":0.0144,"search_context_size_medium":0.0144}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supports_web_search": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna": { "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -64933,21 +70867,38 @@ "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "input_cost_per_token": 2.7e-07, - "input_cost_per_token_above_272k_tokens": 5.4e-07, - "cache_creation_input_token_cost": 3.375e-07, - "cache_creation_input_token_cost_above_272k_tokens": 6.75e-07, - "cache_read_input_token_cost": 2.7e-08, - "cache_read_input_token_cost_above_272k_tokens": 5.4e-08, - "output_cost_per_token": 1.62e-06, - "output_cost_per_token_above_272k_tokens": 2.43e-06, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html" + "input_cost_per_token": 2.64e-07, + "input_cost_per_token_above_272k_tokens": 5.28e-07, + "cache_creation_input_token_cost": 3.3e-07, + "cache_creation_input_token_cost_above_272k_tokens": 6.6e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 3.3e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.32e-06, + "cache_creation_input_token_cost_flex": 1.65e-07, + "cache_creation_input_token_cost_priority": 6.6e-07, + "cache_read_input_token_cost": 2.64e-08, + "cache_read_input_token_cost_above_272k_tokens": 5.28e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.64e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.056e-07, + "cache_read_input_token_cost_flex": 1.32e-08, + "cache_read_input_token_cost_priority": 5.28e-08, + "input_cost_per_token_above_272k_tokens_flex": 2.64e-07, + "input_cost_per_token_above_272k_tokens_priority": 1.056e-06, + "input_cost_per_token_flex": 1.32e-07, + "input_cost_per_token_priority": 5.28e-07, + "output_cost_per_token": 1.584e-06, + "output_cost_per_token_above_272k_tokens": 2.376e-06, + "output_cost_per_token_above_272k_tokens_flex": 1.188e-06, + "output_cost_per_token_above_272k_tokens_priority": 4.752e-06, + "output_cost_per_token_flex": 7.92e-07, + "output_cost_per_token_priority": 3.168e-06, + "search_context_cost_per_query": {"search_context_size_high":0.0144,"search_context_size_low":0.0144,"search_context_size_medium":0.0144}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supports_web_search": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.4": { "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -64968,17 +70919,18 @@ "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "input_cost_per_token": 3.375e-06, - "cache_read_input_token_cost": 3.375e-07, - "output_cost_per_token": 2.025e-05, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html" + "input_cost_per_token": 3.3e-06, + "cache_read_input_token_cost": 3.3e-07, + "output_cost_per_token": 1.98e-05, + "search_context_cost_per_query": {"search_context_size_high":0.0144,"search_context_size_low":0.0144,"search_context_size_medium":0.0144}, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", + "supports_web_search": true }, "bedrock_mantle/us-gov-west-1/xai.grok-4.3": { "use_openai_responses_path": true, "litellm_provider": "bedrock_mantle", "max_input_tokens": 1048576, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -64989,21 +70941,36 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "input_cost_per_token": 1.5e-06, "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 2.4e-07 + "cache_read_input_token_cost": 2.4e-07, + "cache_read_input_token_cost_batches": 1.2e-07, + "cache_read_input_token_cost_flex": 1.2e-07, + "cache_read_input_token_cost_priority": 4.2e-07, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_flex": 7.5e-07, + "input_cost_per_token_priority": 2.625e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.25e-06 }, "bedrock_mantle/us-gov-west-1/xai.grok-4.6": { "use_openai_responses_path": true, "input_cost_per_token": 2.64e-06, "output_cost_per_token": 7.92e-06, "cache_read_input_token_cost": 6.6e-07, + "cache_read_input_token_cost_flex": 3.3e-07, + "cache_read_input_token_cost_priority": 1.155e-06, + "input_cost_per_token_flex": 1.32e-06, + "input_cost_per_token_priority": 4.62e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", + "output_cost_per_token_flex": 3.96e-06, + "output_cost_per_token_priority": 1.386e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -65017,12 +70984,17 @@ }, "bedrock_mantle/us-gov-west-1/google.gemma-4-e2b": { "input_cost_per_token": 4.8e-08, + "input_cost_per_token_flex": 2.4e-08, + "input_cost_per_token_priority": 8.4e-08, "output_cost_per_token": 9.6e-08, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 4.8e-08, + "output_cost_per_token_flex": 4.8e-08, + "output_cost_per_token_priority": 1.68e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -65036,12 +71008,18 @@ }, "bedrock_mantle/us-gov-west-1/google.gemma-4-26b-a4b": { "input_cost_per_token": 1.56e-07, + "input_cost_per_token_batches": 7.8e-08, + "input_cost_per_token_flex": 7.8e-08, + "input_cost_per_token_priority": 2.73e-07, "output_cost_per_token": 4.8e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", + "output_cost_per_token_batches": 2.4e-07, + "output_cost_per_token_flex": 2.4e-07, + "output_cost_per_token_priority": 8.4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -65055,12 +71033,18 @@ }, "bedrock_mantle/us-gov-west-1/google.gemma-4-31b": { "input_cost_per_token": 1.68e-07, + "input_cost_per_token_batches": 8.4e-08, + "input_cost_per_token_flex": 8.4e-08, + "input_cost_per_token_priority": 2.94e-07, "output_cost_per_token": 4.8e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", + "output_cost_per_token_batches": 2.4e-07, + "output_cost_per_token_flex": 2.4e-07, + "output_cost_per_token_priority": 8.4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -65073,14 +71057,20 @@ "supports_vision": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-oss-20b": { + "supports_vision": false, "input_cost_per_token": 8.4e-08, + "input_cost_per_token_batches": 4.2e-08, + "input_cost_per_token_flex": 4.2e-08, + "input_cost_per_token_priority": 1.47e-07, "output_cost_per_token": 3.6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", + "output_cost_per_token_batches": 1.8e-07, + "output_cost_per_token_flex": 1.8e-07, + "output_cost_per_token_priority": 6.3e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -65092,14 +71082,20 @@ "supports_tool_choice": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-oss-120b": { + "supports_vision": false, "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, "output_cost_per_token": 7.2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -65120,7 +71116,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.4e-05, "prompt_cache_min_tokens": 512, @@ -65143,7 +71138,8 @@ "supports_xhigh_reasoning_effort": true, "thinking_always_on": true, "supports_forced_tool_use": false, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html", + "token_count_model": {"model":"anthropic.claude-opus-5-5","litellm_provider":"bedrock_mantle","region":"us-gov-west-1"} }, "bedrock_mantle/us-gov-west-1/anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -65156,7 +71152,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "supports_forced_tool_use": false, @@ -65179,13 +71174,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": {"model":"anthropic.claude-sonnet-5-5","litellm_provider":"bedrock_mantle","region":"us-gov-west-1"} }, "bedrock_mantle/us-gov-east-1/openai.gpt-5.4": { "litellm_provider": "bedrock_mantle", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -65208,18 +71203,25 @@ "supports_vision": true, "input_cost_per_token": 3.3e-06, "cache_read_input_token_cost": 3.3e-07, - "output_cost_per_token": 1.98e-05 + "output_cost_per_token": 1.98e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.md" }, "bedrock_mantle/us-gov-east-1/xai.grok-4.6": { "use_openai_responses_path": true, "input_cost_per_token": 2.64e-06, "output_cost_per_token": 7.92e-06, "cache_read_input_token_cost": 6.6e-07, + "cache_read_input_token_cost_flex": 3.3e-07, + "cache_read_input_token_cost_priority": 1.155e-06, + "input_cost_per_token_flex": 1.32e-06, + "input_cost_per_token_priority": 4.62e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", + "output_cost_per_token_flex": 3.96e-06, + "output_cost_per_token_priority": 1.386e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -65232,14 +71234,20 @@ "supports_vision": true }, "bedrock_mantle/us-gov-east-1/openai.gpt-oss-20b": { + "supports_vision": false, "input_cost_per_token": 8.4e-08, + "input_cost_per_token_batches": 4.2e-08, + "input_cost_per_token_flex": 4.2e-08, + "input_cost_per_token_priority": 1.47e-07, "output_cost_per_token": 3.6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", + "output_cost_per_token_batches": 1.8e-07, + "output_cost_per_token_flex": 1.8e-07, + "output_cost_per_token_priority": 6.3e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -65251,14 +71259,20 @@ "supports_tool_choice": true }, "bedrock_mantle/us-gov-east-1/openai.gpt-oss-120b": { + "supports_vision": false, "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, "output_cost_per_token": 7.2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -65271,106 +71285,128 @@ }, "bedrock_mantle/deepseek.v3.1": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 5.8e-07, + "input_cost_per_token_batches": 2.9e-07, "input_cost_per_token_flex": 2.9e-07, + "input_cost_per_token_priority": 1.015e-06, "output_cost_per_token": 1.68e-06, "output_cost_per_token_flex": 8.4e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 8.4e-07, + "output_cost_per_token_priority": 2.94e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_flex": 1.25e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.38e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-235b-a22b-2507": { "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, "input_cost_per_token_flex": 1.1e-07, + "input_cost_per_token_priority": 3.85e-07, "output_cost_per_token": 8.8e-07, "output_cost_per_token_flex": 4.4e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 4.4e-07, + "output_cost_per_token_priority": 1.54e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-32b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 32000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-32b.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-30b-a3b-instruct.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html", "input_cost_per_token": 4.5e-07, + "input_cost_per_token_batches": 2.25e-07, "input_cost_per_token_flex": 2.25e-07, + "input_cost_per_token_priority": 7.875e-07, "output_cost_per_token": 1.8e-06, "output_cost_per_token_flex": 9e-07, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 9e-07, + "output_cost_per_token_priority": 3.15e-06, "supported_endpoints": [ "/v1/chat/completions" ], @@ -65380,39 +71416,45 @@ }, "bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct": { "input_cost_per_token": 1.4e-07, + "input_cost_per_token_batches": 7e-08, "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct": { "input_cost_per_token": 5.3e-07, + "input_cost_per_token_batches": 2.6e-07, "input_cost_per_token_flex": 2.6e-07, + "input_cost_per_token_priority": 9.3e-07, "output_cost_per_token": 2.66e-06, "output_cost_per_token_flex": 1.33e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 1.33e-06, + "output_cost_per_token_priority": 4.66e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-vl-235b-a22b.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "azure/us-gov/gpt-5.1": { "cache_read_input_token_cost": 1.71875e-07, @@ -65421,7 +71463,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.375e-05, "supported_endpoints": [ @@ -65455,7 +71496,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.05e-06, "supports_prompt_caching": true, @@ -65468,7 +71508,6 @@ "input_cost_per_token": 1.63e-07, "litellm_provider": "azure", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -65476,7 +71515,6 @@ "input_cost_per_token": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -65507,7 +71545,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_image": 0.04, "output_cost_per_token": 0, @@ -65532,7 +71569,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -65557,7 +71593,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -65582,7 +71617,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/models/lyria-realtime-exp", @@ -65707,6 +71741,7 @@ "cache_read_input_token_cost": 5e-07, "input_cost_per_token_above_272k_tokens": 1e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.4": { @@ -65803,6 +71838,7 @@ "perplexity/google/gemini-3.5-flash-lite": { "litellm_provider": "perplexity", "mode": "responses", + "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 3e-07, @@ -65810,9 +71846,26 @@ "cache_read_input_token_cost": 3e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, + "perplexity/google/gemini-4-argon": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-4-carbon": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, "perplexity/google/gemini-3.6-flash": { "litellm_provider": "perplexity", "mode": "responses", + "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1.5e-06, @@ -65823,6 +71876,7 @@ "perplexity/google/gemini-3.7-flash": { "litellm_provider": "perplexity", "mode": "responses", + "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 7.5e-07, @@ -65935,6 +71989,14 @@ "cache_read_input_token_cost": 1.15e-09, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, + "perplexity/perplexity/nemotron-3.5-super-120b-a12b": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 4e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, "perplexity/perplexity/nemotron-3-ultra-550b-a55b": { "litellm_provider": "perplexity", "mode": "responses", @@ -65952,7 +72014,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://inference.baseten.co/v1/models", @@ -65970,13 +72031,15 @@ "supports_tool_choice": true, "supports_vision": true }, + "baseten/glm-latest": { + "alias_of": "baseten/zai-org/GLM-5.3" + }, "baseten/zai-org/GLM-5.3-Fast": { "cache_read_input_token_cost": 2.1e-07, "input_cost_per_token": 2.1e-06, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://inference.baseten.co/v1/models", @@ -66001,7 +72064,7 @@ "output_cost_per_token": 1.5e-07, "source": "https://api.together.ai/v1/models", "max_input_tokens": 128000, - "max_tokens": 128000 + "max_output_tokens": 128000 }, "vertex_ai/gemini-2.5-flash-native-audio": { "deprecation_date": "2026-12-13", @@ -66056,18 +72119,20 @@ "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "successor_model": "vertex_ai/gemini-omni-1.2-flash" }, "vertex_ai/gemini-omni-1.1-flash-preview": { "input_cost_per_token": 1.5e-06, "litellm_provider": "vertex_ai", + "max_input_tokens": 131072, "max_output_tokens": 57920, - "max_tokens": 57920, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-1-1-flash", + "successor_model": "vertex_ai/gemini-omni-1.2-flash", "supported_endpoints": [ "/v1beta/interactions" ], @@ -66098,6 +72163,19 @@ "litellm_provider": "openai", "mode": "chat", "output_cost_per_token": 7.5e-05, + "fedramp_uplift_multiplier": 1.1, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_reasoning": true + }, + "gpt-5.5-cyber-preview": { + "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2027-02-01", + "deprecation_source": "https://developers.openai.com/api/docs/deprecations", + "input_cost_per_token": 1.25e-05, + "litellm_provider": "openai", + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/pricing", "supports_reasoning": true }, @@ -66116,7 +72194,7 @@ "output_cost_per_token": 3.5e-06, "source": "https://api.together.ai/v1/models", "max_input_tokens": 4096, - "max_tokens": 4096 + "max_output_tokens": 4096 }, "together_ai/meta-llama/Llama-3.2-1B-Instruct": { "input_cost_per_token": 6e-08, @@ -66125,7 +72203,7 @@ "output_cost_per_token": 6e-08, "source": "https://api.together.ai/v1/models", "max_input_tokens": 131072, - "max_tokens": 131072 + "max_output_tokens": 131072 }, "together_ai/meta-llama/Llama-3.2-3B-Instruct": { "input_cost_per_token": 6e-08, @@ -66134,7 +72212,7 @@ "output_cost_per_token": 6e-08, "source": "https://api.together.ai/v1/models", "max_input_tokens": 131072, - "max_tokens": 131072 + "max_output_tokens": 131072 }, "together_ai/Qwen/Qwen2-1.5B-Instruct": { "input_cost_per_token": 2e-08, @@ -66143,7 +72221,7 @@ "output_cost_per_token": 2e-08, "source": "https://api.together.ai/v1/models", "max_input_tokens": 32768, - "max_tokens": 32768 + "max_output_tokens": 32768 }, "together_ai/Qwen/Qwen2.5-14B-Instruct": { "input_cost_per_token": 8e-07, @@ -66152,7 +72230,7 @@ "output_cost_per_token": 8e-07, "source": "https://api.together.ai/v1/models", "max_input_tokens": 32768, - "max_tokens": 32768 + "max_output_tokens": 32768 }, "together_ai/Qwen/Qwen2.5-72B-Instruct": { "input_cost_per_token": 1.2e-06, @@ -66161,14 +72239,14 @@ "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", "max_input_tokens": 32768, - "max_tokens": 32768 + "max_output_tokens": 32768 }, "together_ai/Salesforce/Llama-Rank-V1": { "deprecation_date": "2026-02-06", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://api.together.ai/v1/models" @@ -66177,7 +72255,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 16384, "mode": "completion", "output_cost_per_token": 2e-07, "source": "https://api.together.xyz/v1/models" @@ -66190,132 +72268,90 @@ "output_cost_per_token": 0.0, "source": "https://api.together.ai/v1/models" }, - "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/Qwen/QwQ-32B": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 1.2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/Qwen/Qwen2-72B-Instruct": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 9e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 9e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/Qwen/Qwen2-VL-72B-Instruct": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 1.2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models" - }, "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { "deprecation_date": "2026-02-06", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models" }, - "together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models" - }, "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { "deprecation_date": "2026-01-05", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.95e-06, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { "deprecation_date": "2026-06-04", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Coder-Next-FP8": { "deprecation_date": "2026-05-14", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { "deprecation_date": "2026-04-02", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { "deprecation_date": "2026-02-25", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-VL-32B-Instruct": { "deprecation_date": "2026-02-25", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-VL-8B-Instruct": { "deprecation_date": "2026-04-16", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 6.8e-07, "source": "https://api.together.ai/v1/models" @@ -66323,170 +72359,96 @@ "together_ai/Qwen/Qwen3.5-397B-A17B": { "cache_read_input_token_cost": 3.5e-07, "deprecation_date": "2026-06-29", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.6e-06, "source": "https://api.together.ai/v1/models" }, - "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "deprecation_date": "2025-12-23", - "input_cost_per_token": 2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 1.6e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.6e-06, - "source": "https://api.together.ai/v1/models" - }, "together_ai/deepseek-ai/DeepSeek-V3.1": { "deprecation_date": "2026-05-14", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.7e-06, "source": "https://api.together.ai/v1/models" }, - "together_ai/deepseek-ai/deepseek-coder-33b-instruct": { - "deprecation_date": "2024-08-22", - "input_cost_per_token": 8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/google/gemma-2-27b-it": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 8e-07, + "together_ai/essentialai/rnj-1-instruct": { + "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", - "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models" + "output_cost_per_token": 1.5e-07, + "source": "https://www.together.ai/models/rnj-1-instruct" }, "together_ai/google/gemma-4-31B-it": { "deprecation_date": "2026-09-15", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 3.9e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 9.7e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/meta-llama/Llama-3-8b-chat-hf": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://api.together.ai/v1/models" + "source": "https://api.together.ai/v1/models", + "successor_model": "together_ai/zai-org/GLM-5.3-Flash" }, "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { "deprecation_date": "2026-02-06", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5.9e-07, "source": "https://api.together.ai/v1/models" }, - "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": { - "deprecation_date": "2025-12-23", - "input_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8.8e-07, - "source": "https://api.together.ai/v1/models" - }, - "together_ai/meta-llama/Meta-Llama-3-8B-Instruct": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://api.together.ai/v1/models" - }, "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { "deprecation_date": "2026-02-25", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { "deprecation_date": "2026-03-06", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://api.together.ai/v1/models" }, - "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://api.together.ai/v1/models" - }, "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { "deprecation_date": "2026-04-02", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { "deprecation_date": "2026-04-16", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.together.ai/v1/models" @@ -66494,10 +72456,11 @@ "together_ai/moonshotai/Kimi-K2.6": { "cache_read_input_token_cost": 2e-07, "deprecation_date": "2026-08-19", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://api.together.ai/v1/models" @@ -66505,71 +72468,68 @@ "together_ai/moonshotai/Kimi-K2.7-Code": { "cache_read_input_token_cost": 1.9e-07, "deprecation_date": "2026-08-27", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 9.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.together.ai/v1/models" }, - "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { - "deprecation_date": "2025-08-28", - "input_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 8.8e-07, - "source": "https://api.together.ai/v1/models" - }, "together_ai/nvidia/nemotron-3-ultra-550b-a55b": { "cache_read_input_token_cost": 2e-07, "deprecation_date": "2026-08-27", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 512288, - "max_tokens": 512288, + "max_output_tokens": 512288, "mode": "chat", "output_cost_per_token": 3.6e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/openai/gpt-oss-20b": { "deprecation_date": "2026-09-15", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://api.together.ai/v1/models" + "source": "https://api.together.ai/v1/models", + "successor_model": "together_ai/Qwen/Qwen3.5-9B" }, "together_ai/zai-org/GLM-4.5-Air-FP8": { "deprecation_date": "2026-04-02", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.1e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-4.7": { "deprecation_date": "2026-04-02", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 4.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 202752, - "max_tokens": 202752, + "max_output_tokens": 202752, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-5": { "deprecation_date": "2026-06-22", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "max_input_tokens": 202752, - "max_tokens": 202752, + "max_output_tokens": 202752, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://api.together.ai/v1/models" @@ -66577,16 +72537,18 @@ "together_ai/zai-org/GLM-5.1": { "cache_read_input_token_cost": 2.6e-07, "deprecation_date": "2026-07-10", + "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.4e-06, "litellm_provider": "together_ai", "max_input_tokens": 202752, - "max_tokens": 202752, + "max_output_tokens": 202752, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.together.ai/v1/models" }, "azure/eu/codex-mini": { "deprecation_date": "2026-11-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 4.13e-07, "input_cost_per_token": 1.65e-06, "litellm_provider": "azure", @@ -66603,6 +72565,8 @@ }, "azure/eu/gpt-4.1": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_priority": 9.63e-07, "input_cost_per_token": 2.2e-06, @@ -66613,10 +72577,17 @@ "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-mini": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.4-mini", "cache_read_input_token_cost": 1.1e-07, "cache_read_input_token_cost_priority": 1.93e-07, "input_cost_per_token": 4.4e-07, @@ -66627,10 +72598,17 @@ "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-nano": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.4-nano", "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 5.5e-08, @@ -66641,13 +72619,14 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4o-2024-05-13": { - "deprecation_date": "2026-12-09", + "deprecation_date": "2027-01-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1", "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, @@ -66655,6 +72634,8 @@ }, "azure/eu/gpt-5": { "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1", "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_batches": 6.875e-08, "cache_read_input_token_cost_priority": 2.75e-07, @@ -66666,10 +72647,17 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-codex": { "deprecation_date": "2027-03-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.1-codex", "cache_read_input_token_cost": 1.38e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", @@ -66678,7 +72666,9 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-mini": { - "deprecation_date": "2027-02-09", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.4-mini", "cache_read_input_token_cost": 2.75e-08, "cache_read_input_token_cost_batches": 1.375e-08, "cache_read_input_token_cost_priority": 4.95e-08, @@ -66690,10 +72680,17 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-nano": { "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.4-nano", "cache_read_input_token_cost": 5.5e-09, "cache_read_input_token_cost_batches": 2.75e-09, "input_cost_per_token": 5.5e-08, @@ -66702,20 +72699,33 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-pro": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.2-pro", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex-max": { "deprecation_date": "2027-05-18", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", @@ -66725,6 +72735,8 @@ }, "azure/eu/gpt-5.2": { "deprecation_date": "2027-06-08", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.4", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_batches": 9.625e-08, "cache_read_input_token_cost_priority": 3.85e-07, @@ -66736,10 +72748,17 @@ "output_cost_per_token": 1.54e-05, "output_cost_per_token_batches": 7.7e-06, "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-codex": { "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.3-codex", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", @@ -66754,10 +72773,16 @@ "mode": "responses", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.3-codex": { "deprecation_date": "2027-08-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 1.925e-06, @@ -66766,10 +72791,17 @@ "mode": "responses", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-mini": { + "default_reasoning_effort": "none", "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 8.25e-08, "cache_read_input_token_cost_batches": 4.125e-08, "cache_read_input_token_cost_priority": 1.65e-07, @@ -66781,10 +72813,17 @@ "output_cost_per_token": 4.95e-06, "output_cost_per_token_batches": 2.475e-06, "output_cost_per_token_priority": 9.9e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-nano": { + "default_reasoning_effort": "none", "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.2e-08, "cache_read_input_token_cost_batches": 1.1e-08, "input_cost_per_token": 2.2e-07, @@ -66793,10 +72832,16 @@ "mode": "chat", "output_cost_per_token": 1.375e-06, "output_cost_per_token_batches": 6.875e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-pro": { "deprecation_date": "2027-09-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 3.3e-05, "input_cost_per_token_above_272k_tokens": 6.6e-05, "input_cost_per_token_above_272k_tokens_batches": 3.3e-05, @@ -66807,6 +72852,11 @@ "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_above_272k_tokens_batches": 0.0001485, "output_cost_per_token_batches": 9.9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-6-astra": { @@ -66820,10 +72870,14 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_above_272k_tokens": 9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_endpoints": [ "/v1/chat/completions", @@ -66841,7 +72895,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -66864,14 +72918,13 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_above_272k_tokens": 9e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ @@ -66913,14 +72966,13 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ @@ -66961,22 +73013,48 @@ "output_cost_per_token_batches": 2.42e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, + "azure/eu/o3": { + "deprecation_date": "2026-11-19", + "successor_model": "azure/eu/gpt-5.6-sol", + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, "azure/eu/o3-2025-04-16": { "deprecation_date": "2026-11-19", + "successor_model": "azure/eu/gpt-5.6-sol", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-deep-research": { "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6-sol", "cache_read_input_token_cost": 2.75e-06, "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", @@ -66984,22 +73062,49 @@ "output_cost_per_token": 4.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, + "azure/eu/o4-mini": { + "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6-terra", + "cache_read_input_token_cost": 3.03e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, "azure/eu/o4-mini-2025-04-16": { "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/eu/gpt-5.6-terra", "cache_read_input_token_cost": 3.03e-07, "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-3-large": { "deprecation_date": "2028-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "mode": "embedding", @@ -67007,6 +73112,7 @@ }, "azure/eu/text-embedding-3-small": { "deprecation_date": "2028-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "mode": "embedding", @@ -67014,6 +73120,7 @@ }, "azure/eu/text-embedding-ada-002": { "deprecation_date": "2028-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "mode": "embedding", @@ -67027,14 +73134,15 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_audio_input": true, + "supports_audio_output": true, "tpm": 250000, "rpm": 10, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, @@ -67049,14 +73157,15 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_audio_input": true, + "supports_audio_output": true, "tpm": 250000, "rpm": 10, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, @@ -67065,6 +73174,7 @@ }, "azure/us/codex-mini": { "deprecation_date": "2026-11-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 4.13e-07, "input_cost_per_token": 1.65e-06, "litellm_provider": "azure", @@ -67081,6 +73191,8 @@ }, "azure/us/gpt-4.1": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_priority": 9.63e-07, "input_cost_per_token": 2.2e-06, @@ -67091,10 +73203,17 @@ "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-mini": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-mini", "cache_read_input_token_cost": 1.1e-07, "cache_read_input_token_cost_priority": 1.93e-07, "input_cost_per_token": 4.4e-07, @@ -67105,10 +73224,17 @@ "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-nano": { "deprecation_date": "2027-04-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-nano", "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 5.5e-08, @@ -67119,13 +73245,14 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4o-2024-05-13": { - "deprecation_date": "2026-12-09", + "deprecation_date": "2027-01-14", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, @@ -67133,6 +73260,8 @@ }, "azure/us/gpt-5": { "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1", "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_batches": 6.875e-08, "cache_read_input_token_cost_priority": 2.75e-07, @@ -67144,10 +73273,17 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-codex": { "deprecation_date": "2027-03-17", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.1-codex", "cache_read_input_token_cost": 1.38e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", @@ -67156,7 +73292,9 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-mini": { - "deprecation_date": "2027-02-09", + "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-mini", "cache_read_input_token_cost": 2.75e-08, "cache_read_input_token_cost_batches": 1.375e-08, "cache_read_input_token_cost_priority": 4.95e-08, @@ -67168,10 +73306,17 @@ "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-nano": { "deprecation_date": "2027-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4-nano", "cache_read_input_token_cost": 5.5e-09, "cache_read_input_token_cost_batches": 2.75e-09, "input_cost_per_token": 5.5e-08, @@ -67180,20 +73325,33 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-pro": { "deprecation_date": "2027-04-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.2-pro", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex-max": { "deprecation_date": "2027-05-18", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", @@ -67203,6 +73361,8 @@ }, "azure/us/gpt-5.2": { "deprecation_date": "2027-06-08", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.4", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_batches": 9.625e-08, "cache_read_input_token_cost_priority": 3.85e-07, @@ -67214,10 +73374,17 @@ "output_cost_per_token": 1.54e-05, "output_cost_per_token_batches": 7.7e-06, "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-codex": { "deprecation_date": "2027-07-13", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.3-codex", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", @@ -67232,10 +73399,16 @@ "mode": "responses", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.3-codex": { "deprecation_date": "2027-08-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 1.925e-06, @@ -67244,10 +73417,17 @@ "mode": "responses", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-mini": { + "default_reasoning_effort": "none", "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 8.25e-08, "cache_read_input_token_cost_batches": 4.125e-08, "cache_read_input_token_cost_priority": 1.65e-07, @@ -67259,10 +73439,17 @@ "output_cost_per_token": 4.95e-06, "output_cost_per_token_batches": 2.475e-06, "output_cost_per_token_priority": 9.9e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-nano": { + "default_reasoning_effort": "none", "deprecation_date": "2027-09-21", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.2e-08, "cache_read_input_token_cost_batches": 1.1e-08, "input_cost_per_token": 2.2e-07, @@ -67271,10 +73458,16 @@ "mode": "chat", "output_cost_per_token": 1.375e-06, "output_cost_per_token_batches": 6.875e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-pro": { "deprecation_date": "2027-09-07", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 3.3e-05, "input_cost_per_token_above_272k_tokens": 6.6e-05, "input_cost_per_token_above_272k_tokens_batches": 3.3e-05, @@ -67285,6 +73478,11 @@ "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_above_272k_tokens_batches": 0.0001485, "output_cost_per_token_batches": 9.9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/o1-mini": { @@ -67299,6 +73497,8 @@ }, "azure/us/o3-deep-research": { "deprecation_date": "2026-11-19", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/us/gpt-5.6-sol", "cache_read_input_token_cost": 2.75e-06, "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", @@ -67308,6 +73508,7 @@ }, "azure/us/text-embedding-3-large": { "deprecation_date": "2028-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "mode": "embedding", @@ -67315,6 +73516,7 @@ }, "azure/us/text-embedding-3-small": { "deprecation_date": "2028-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "mode": "embedding", @@ -67322,27 +73524,33 @@ }, "azure/us/text-embedding-ada-002": { "deprecation_date": "2028-02-09", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-realtime-2": { + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, - "deprecation_date": "2026-10-31", + "deprecation_date": "2027-01-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "successor_model": "azure/gpt-realtime-2.1", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/realtime" ], @@ -67386,7 +73594,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "audio_transcription", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ @@ -67400,7 +73607,11 @@ "supported_output_modalities": [ "text" ], - "supports_audio_input": true + "supports_audio_input": true, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "supports_native_streaming": true }, "azure/gpt-transcribe": { "deprecation_date": "2028-02-01", @@ -67410,7 +73621,8 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/audio/transcriptions", - "/v1/realtime/transcription_sessions" + "/v1/realtime/transcription_sessions", + "/v1/realtime" ], "supported_modalities": [ "text", @@ -67419,7 +73631,13 @@ "supported_output_modalities": [ "text" ], - "supports_audio_input": true + "supports_audio_input": true, + "provider_specific_entry": { + "realtime_ga_only": 1, + "transcription_json_or_text_only": 1, + "transcription_usage_duration": 1 + }, + "supports_native_streaming": true }, "azure/gpt-realtime-translate": { "deprecation_date": "2027-11-09", @@ -67427,7 +73645,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ @@ -67438,14 +73655,17 @@ "audio" ], "supports_audio_input": true, - "supports_audio_output": true + "supports_audio_output": true, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "supports_native_streaming": true }, "aihubmix/agnes-2.5-flash": { "input_cost_per_token": 3e-08, "litellm_provider": "aihubmix", "max_input_tokens": 512000, "max_output_tokens": 65500, - "max_tokens": 65500, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://aihubmix.com/api/v1/models", @@ -67458,7 +73678,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://aihubmix.com/api/v1/models", @@ -67471,7 +73690,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 200000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-07, "source": "https://aihubmix.com/api/v1/models", @@ -67486,7 +73704,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -67507,7 +73724,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aihubmix.com/api/v1/models", @@ -67525,7 +73741,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -67545,7 +73760,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -67566,7 +73780,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://aihubmix.com/api/v1/models", @@ -67585,7 +73798,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-07, "source": "https://aihubmix.com/api/v1/models", @@ -67600,7 +73812,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.61333e-06, "source": "https://aihubmix.com/api/v1/models", @@ -67629,7 +73840,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.6e-07, "source": "https://aihubmix.com/api/v1/models", @@ -67645,7 +73855,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://aihubmix.com/api/v1/models", @@ -67659,7 +73868,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://aihubmix.com/api/v1/models", @@ -67674,7 +73882,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.84e-07, "source": "https://aihubmix.com/api/v1/models", @@ -67689,7 +73896,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.38e-06, "source": "https://aihubmix.com/api/v1/models", @@ -67704,7 +73910,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.411e-06, "source": "https://aihubmix.com/api/v1/models", @@ -67720,7 +73925,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.4246e-07, "source": "https://aihubmix.com/api/v1/models", @@ -67737,7 +73941,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.0136e-07, "source": "https://aihubmix.com/api/v1/models", @@ -67754,7 +73957,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.411e-06, "source": "https://aihubmix.com/api/v1/models", @@ -67771,7 +73973,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.32375e-06, "source": "https://aihubmix.com/api/v1/models", @@ -67788,7 +73989,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 119000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.5353e-06, "source": "https://aihubmix.com/api/v1/models", @@ -67801,7 +74001,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://aihubmix.com/api/v1/models", @@ -67818,7 +74017,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://aihubmix.com/api/v1/models", @@ -67835,7 +74033,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://aihubmix.com/api/v1/models", @@ -67852,7 +74049,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://aihubmix.com/api/v1/models", @@ -67869,7 +74065,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.499999e-06, "source": "https://aihubmix.com/api/v1/models", @@ -67877,6 +74072,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_vision": true, "supports_web_search": true }, @@ -67886,7 +74082,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.75e-06, "source": "https://aihubmix.com/api/v1/models", @@ -67894,6 +74089,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_vision": true, "supports_web_search": true }, @@ -67902,7 +74098,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 131100, - "max_tokens": 131100, "mode": "chat", "output_cost_per_token": 3.9998e-07, "source": "https://aihubmix.com/api/v1/models", @@ -67914,7 +74109,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 131100, - "max_tokens": 131100, "mode": "chat", "output_cost_per_token": 3.9998e-07, "source": "https://aihubmix.com/api/v1/models", @@ -67927,7 +74121,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 7.889e-06, "source": "https://aihubmix.com/api/v1/models", @@ -67942,7 +74135,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.9438e-06, "source": "https://aihubmix.com/api/v1/models", @@ -67957,7 +74149,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.9438e-07, "source": "https://aihubmix.com/api/v1/models", @@ -67973,7 +74164,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 200000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.09848e-06, "source": "https://aihubmix.com/api/v1/models", @@ -67987,7 +74177,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://aihubmix.com/api/v1/models", @@ -68003,7 +74192,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -68020,7 +74208,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -68037,7 +74224,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68054,7 +74240,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68071,7 +74256,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://aihubmix.com/api/v1/models", @@ -68087,7 +74271,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00018, "source": "https://aihubmix.com/api/v1/models", @@ -68104,7 +74287,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68121,7 +74303,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "source": "https://aihubmix.com/api/v1/models", @@ -68138,7 +74319,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://aihubmix.com/api/v1/models", @@ -68154,7 +74334,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://aihubmix.com/api/v1/models", @@ -68199,7 +74378,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68215,7 +74393,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68231,7 +74408,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.248e-07, "source": "https://aihubmix.com/api/v1/models", @@ -68247,7 +74423,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.535e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68263,7 +74438,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.9995e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68279,7 +74453,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.999e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68295,7 +74468,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -68311,7 +74483,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.0984e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68324,7 +74495,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68360,7 +74530,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 204800, "max_output_tokens": 204800, - "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.1832e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68374,7 +74543,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 524288, - "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.152e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68399,7 +74567,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 5.48e-07, "source": "https://aihubmix.com/api/v1/models", @@ -68411,7 +74578,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 9.008e-07, "source": "https://aihubmix.com/api/v1/models", @@ -68426,7 +74592,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 9.864e-07, "source": "https://aihubmix.com/api/v1/models", @@ -68441,7 +74606,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.532e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68456,7 +74620,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.524e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68473,7 +74636,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.608e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68490,7 +74652,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.128e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68507,7 +74668,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68524,7 +74684,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.80025e-07, "source": "https://aihubmix.com/api/v1/models", @@ -68542,7 +74701,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5.07e-06, "source": "https://aihubmix.com/api/v1/models", @@ -68565,6 +74723,235 @@ "supports_reasoning": true, "supports_vision": true }, + "aiand/deepseek-ai/deepseek-v4-flash": { + "cache_read_input_token_cost": 8e-08, + "deprecation_date": "2026-10-27", + "input_cost_per_token": 1.5e-07, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "aiand/deepseek-ai/deepseek-v4-pro": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "aiand/deepseek-ai/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 2e-08, + "deprecation_date": "2026-11-05", + "input_cost_per_token": 3e-07, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "aiand/deepseek-ai/deepseek-v4.1-flash-1017": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "aiand/google/gemma-4-31b-it": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "aiand", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "aiand/meta/muse-spark-open": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "aiand/moonshotai/kimi-k2.7-code": { + "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2026-10-27", + "input_cost_per_token": 7.5e-07, + "litellm_provider": "aiand", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "aiand/moonshotai/kimi-k3": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.25e-05, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "aiand/motif-technologies/motif-3": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 5e-07, + "litellm_provider": "aiand", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "aiand/openai/gpt-oss-120b": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "aiand", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "aiand/qwen/qwen3.6-27b": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 3.2e-07, + "litellm_provider": "aiand", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "aiand/qwen/qwen3.8-27b": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-07, + "litellm_provider": "aiand", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "aiand/zai-org/glm-5.2": { + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-10-27", + "input_cost_per_token": 1e-06, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "aiand/zai-org/glm-5.3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "aiand", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "aiand/zai-org/glm-5.3-flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "aiand", + "max_input_tokens": 1048550, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://api.aiand.com/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, "bespoke/nimble-latest": { "input_cost_per_token": 0.0, "litellm_provider": "bespoke", @@ -68656,36 +75043,104 @@ "notes": "Self-hosted decision model; infrastructure costs are paid separately" } }, + "nace/drex-v1.0": { + "input_cost_per_token": 4e-08, + "litellm_provider": "nace", + "max_input_tokens": 32768, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" + }, + "nace/drex-v1.5": { + "input_cost_per_token": 5e-08, + "litellm_provider": "nace", + "max_input_tokens": 131072, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" + }, + "nace/drex-v2.0": { + "input_cost_per_token": 6e-08, + "litellm_provider": "nace", + "max_input_tokens": 131072, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" + }, + "nace/drex-latest": { + "input_cost_per_token": 6e-08, + "litellm_provider": "nace", + "max_input_tokens": 131072, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" + }, "typesafe/jev-1.13.0": { "input_cost_per_token": 4.2e-08, "litellm_provider": "typesafe", + "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.typesafe.ai/models" }, + "typesafe/jev-1.14.0": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "typesafe", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.typesafe.ai/models", + "supports_box_questions": true + }, "typesafe/jev-latest": { "input_cost_per_token": 4.2e-08, "litellm_provider": "typesafe", + "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, - "source": "https://docs.typesafe.ai/models" + "source": "https://docs.typesafe.ai/models", + "supports_box_questions": true }, "typesafe/jev-preview": { "input_cost_per_token": 4.2e-08, "litellm_provider": "typesafe", + "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, - "source": "https://docs.typesafe.ai/models" + "source": "https://docs.typesafe.ai/models", + "supports_box_questions": true + }, + "eu_jev/eu-jeff-1.0.0": { + "input_cost_per_token": 4.15e-08, + "litellm_provider": "eu_jev", + "max_input_tokens": 32768, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://eu-jev.com/docs", + "supported_endpoints": [ + "/v1/systemone" + ] + }, + "eu_jev/eu-jeff-latest": { + "input_cost_per_token": 4.15e-08, + "litellm_provider": "eu_jev", + "max_input_tokens": 32768, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://eu-jev.com/docs", + "supported_endpoints": [ + "/v1/systemone" + ] }, "wandb/deepseek-ai/DeepSeek-V4.1-Flash": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 2e-07, + "cache_read_input_token_cost": 2e-09, + "input_cost_per_token": 1.3e-07, "litellm_provider": "wandb", "max_input_tokens": 1049000, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.5e-07, - "source": "https://wandb.ai/site/pricing/tokens/", + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": true @@ -68695,7 +75150,7 @@ "input_cost_per_token": 1e-07, "litellm_provider": "wandb", "max_input_tokens": 262000, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://wandb.ai/site/pricing/tokens/", @@ -68706,13 +75161,13 @@ "supports_vision": true }, "wandb/zai-org/GLM-5.3-Flash": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 1.5e-07, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.2e-07, "litellm_provider": "wandb", "max_input_tokens": 1049000, "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://docs.wandb.ai/inference/models.md", + "output_cost_per_token": 3.8e-07, + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -68732,9 +75187,10 @@ "input_cost_per_token_flex": 1.65e-06, "input_cost_per_token_priority": 5.775e-06, "litellm_provider": "bedrock_converse", + "token_count_framing": 64, + "token_count_tokenizer": "kimi_k3", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_flex": 8.25e-06, @@ -68762,9 +75218,10 @@ "input_cost_per_token_flex": 1.5e-06, "input_cost_per_token_priority": 5.25e-06, "litellm_provider": "bedrock_converse", + "token_count_framing": 64, + "token_count_tokenizer": "kimi_k3", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_flex": 7.5e-06, @@ -68780,6 +75237,9 @@ "supports_tool_choice": true, "supports_vision": true }, + "bedrock/kimi-latest": { + "alias_of": "global.moonshotai.kimi-k3" + }, "us.moonshotai.kimi-k3": { "supports_regex_lookaround": false, "cache_creation_input_token_cost": 4.125e-06, @@ -68792,9 +75252,10 @@ "input_cost_per_token_flex": 1.65e-06, "input_cost_per_token_priority": 5.775e-06, "litellm_provider": "bedrock_converse", + "token_count_framing": 64, + "token_count_tokenizer": "kimi_k3", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_flex": 8.25e-06, @@ -68816,7 +75277,6 @@ "litellm_provider": "xiaomi_mimo", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.7e-07, "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", @@ -68839,7 +75299,6 @@ "litellm_provider": "xiaomi_mimo", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", @@ -68864,7 +75323,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, @@ -68890,7 +75348,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -68912,7 +75369,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -68934,7 +75390,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -68956,7 +75411,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -68977,7 +75431,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -68999,7 +75452,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -69020,7 +75472,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -69042,7 +75493,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -69064,7 +75514,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -69085,7 +75534,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -69107,7 +75555,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -69129,7 +75576,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -69150,7 +75596,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -69172,7 +75617,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -69197,7 +75641,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -69222,7 +75665,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -69247,7 +75689,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -69268,7 +75709,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -69290,7 +75730,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://inference.baseten.co/v1/models", @@ -69302,12 +75741,12 @@ "supports_vision": true }, "baseten/moonshotai/Kimi-K2.6": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "baseten", "max_input_tokens": 262000, "max_output_tokens": 262000, - "max_tokens": 262000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://inference.baseten.co/v1/models", @@ -69319,12 +75758,12 @@ "supports_vision": true }, "baseten/moonshotai/Kimi-K2.7-Code": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "baseten", "max_input_tokens": 262000, "max_output_tokens": 262000, - "max_tokens": 262000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://inference.baseten.co/v1/models", @@ -69341,7 +75780,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://inference.baseten.co/v1/models", @@ -69352,13 +75790,15 @@ "supports_tool_choice": true, "supports_vision": true }, + "baseten/kimi-latest": { + "alias_of": "baseten/moonshotai/Kimi-K3" + }, "baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "max_input_tokens": 202800, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://inference.baseten.co/v1/models", @@ -69370,12 +75810,12 @@ "supports_vision": false }, "baseten/thinkingmachines/inkling": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1e-06, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4.05e-06, "source": "https://inference.baseten.co/v1/models", @@ -69387,12 +75827,12 @@ "supports_vision": true }, "baseten/thinkingmachines/inkling-small": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://inference.baseten.co/v1/models", @@ -69409,7 +75849,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://inference.baseten.co/v1/models", @@ -69426,7 +75865,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inference.baseten.co/v1/models", @@ -69437,13 +75875,15 @@ "supports_tool_choice": true, "supports_vision": true }, + "baseten/glm-flash-latest": { + "alias_of": "baseten/zai-org/GLM-5.3-Flash" + }, "baseten/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.3e-07, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.6e-07, "source": "https://inference.baseten.co/v1/models", @@ -69454,13 +75894,16 @@ "supports_tool_choice": true, "supports_vision": false }, + "baseten/deepseek-flash-latest": { + "alias_of": "baseten/deepseek-ai/DeepSeek-V4-Flash-0731" + }, "baseten/deepseek-ai/DeepSeek-V4-Pro": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.45e-07, "input_cost_per_token": 1.74e-06, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.48e-06, "source": "https://inference.baseten.co/v1/models", @@ -69477,7 +75920,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://inference.baseten.co/v1/models", @@ -69488,13 +75930,15 @@ "supports_tool_choice": true, "supports_vision": false }, + "baseten/deepseek-pro-latest": { + "alias_of": "baseten/deepseek-ai/DeepSeek-V4-Pro-0813" + }, "baseten/zai-org/GLM-5.2-Fast": { "cache_read_input_token_cost": 2.1e-07, "input_cost_per_token": 2.1e-06, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://inference.baseten.co/v1/models", @@ -69514,7 +75958,6 @@ "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_above_200k_tokens": 4e-06, @@ -69529,17 +75972,19 @@ "xai/grok-code-fast-1": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "deprecation_date": "2026-05-15", + "deprecation_source": "https://docs.x.ai/developers/migration/may-15-retirement", "input_cost_per_image_token": 1e-06, "input_cost_per_token": 1e-06, "input_cost_per_token_above_200k_tokens": 2e-06, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_above_200k_tokens": 4e-06, "source": "https://api.x.ai/v1/language-models", + "successor_model": "xai/grok-build-0.1", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -69556,7 +76001,6 @@ "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_above_200k_tokens": 4e-06, @@ -69577,7 +76021,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.2e-06, @@ -69595,7 +76038,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 196608, "max_output_tokens": 196608, - "max_tokens": 196608, "mode": "chat", "output_cost_per_token_priority": 1.2e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -69622,8 +76064,9 @@ "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_priority": 1.875e-05, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, + "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -69631,6 +76074,8 @@ }, "vertex_ai/gemini-2.0-flash": { "deprecation_date": "2026-06-01", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/gemini-3.5-flash-lite", "input_cost_per_audio_token": 1e-06, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_character": 3.75e-08, @@ -69644,6 +76089,8 @@ }, "vertex_ai/gemini-2.0-flash-lite": { "deprecation_date": "2026-06-01", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/gemini-3.5-flash-lite", "input_cost_per_audio_token": 7.5e-08, "input_cost_per_audio_token_batches": 3.75e-08, "input_cost_per_character": 1.875e-08, @@ -69661,12 +76108,12 @@ "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": ["global"], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -69679,7 +76126,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "output_cost_per_token_batches": 3.6e-07, @@ -69696,9 +76142,10 @@ }, "vertex_ai/veo-3.0-generate-001": { "deprecation_date": "2026-06-30", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/veo-3.1-generate-001", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", @@ -69712,9 +76159,10 @@ }, "vertex_ai/veo-3.0-fast-generate-001": { "deprecation_date": "2026-06-30", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/veo-3.1-fast-generate-001", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -69728,9 +76176,11 @@ ] }, "vertex_ai/veo-2.0-generate-001": { + "deprecation_date": "2026-06-30", + "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", + "successor_model": "vertex_ai/veo-3.1-generate-001", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.5, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", @@ -69777,7 +76227,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -69810,7 +76259,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -69843,7 +76291,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -69876,7 +76323,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -69903,13 +76349,17 @@ "cache_read_input_token_cost": 1.1e-06, "output_cost_per_token": 5.5e-05, "cache_creation_input_token_cost_above_1hr": 2.2e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-mythos-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "apac.anthropic.claude-fable-5": { "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -69925,7 +76375,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -69942,7 +76392,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -69958,7 +76407,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -69978,7 +76427,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, @@ -70002,7 +76450,12 @@ "input_cost_per_token": 5.5e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, "apac.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -70012,7 +76465,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, @@ -70026,6 +76478,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -70036,17 +76490,22 @@ "output_cost_per_token": 2.75e-05, "cache_read_input_token_cost": 5.5e-07, "cache_creation_input_token_cost": 6.875e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, "apac.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, @@ -70060,6 +76519,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, @@ -70069,7 +76529,14 @@ "input_cost_per_token": 5.5e-06, "cache_read_input_token_cost": 5.5e-07, "output_cost_per_token": 2.75e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/ap-northeast-1/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + }, + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.375e-05 }, "apac.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -70079,7 +76546,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, @@ -70093,6 +76559,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, @@ -70104,7 +76571,12 @@ "input_cost_per_token": 4.4e-06, "output_cost_per_token": 2.2e-05, "cache_read_input_token_cost": 2.2e-07, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "apac.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -70113,9 +76585,8 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -70134,7 +76605,11 @@ "cache_read_input_token_cost": 3.3e-07, "cache_creation_input_token_cost": 4.125e-06, "input_cost_per_token": 3.3e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "apac.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -70142,9 +76617,9 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -70158,6 +76633,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -70168,13 +76645,17 @@ "input_cost_per_token": 2.2e-06, "output_cost_per_token": 1.1e-05, "cache_read_input_token_cost": 2.2e-07, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "us.anthropic.claude-mythos-preview": { "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, @@ -70194,7 +76675,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, @@ -70214,7 +76694,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, @@ -70232,11 +76711,11 @@ }, "deepseek.r1-v1:0": { "deprecation_date": "2027-03-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", "input_cost_per_token": 1.35e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", @@ -70249,7 +76728,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -70262,11 +76740,11 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true @@ -70290,10 +76768,14 @@ "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { @@ -70315,6 +76797,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -70330,7 +76813,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, @@ -70346,6 +76828,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -70361,6 +76844,11 @@ "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "au.anthropic.claude-sonnet-5-5": { + "token_count_model": { + "model": "au.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + }, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_1hr": 4.4e-06, @@ -70370,7 +76858,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { @@ -70392,6 +76879,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -70405,13 +76893,12 @@ "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, - "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost": 1e-07, "deprecation_date": "2027-09-29", "input_cost_per_token": 2e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { @@ -70433,10 +76920,14 @@ "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "supports_forced_tool_use": false, + "supports_web_search": true, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" }, + "azure_ai/claude-sonnet-latest": { + "alias_of": "azure_ai/claude-sonnet-5-5" + }, "bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", @@ -70448,7 +76939,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "supports_forced_tool_use": false, @@ -70462,6 +76952,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -70484,7 +76975,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "supports_forced_tool_use": false, @@ -70498,6 +76988,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -70507,7 +76998,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "eu.anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -70519,7 +77015,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { @@ -70541,6 +77036,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -70557,218 +77053,16 @@ "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "token_count_model": { + "model": "global.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" }, - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" - }, - "jp.anthropic.claude-sonnet-5-5": { - "bedrock_converse_supports_strict_tools": false, - "cache_creation_input_token_cost": 2.75e-06, - "cache_creation_input_token_cost_above_1hr": 4.4e-06, - "cache_read_input_token_cost": 1.1e-07, - "input_cost_per_token": 2.2e-06, - "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.1e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" - }, - "perplexity/anthropic/claude-sonnet-5-5": { - "litellm_provider": "perplexity", - "mode": "responses", - "supports_adaptive_thinking": true, - "supports_web_search": true, - "supports_function_calling": true, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 2e-07, - "source": "https://docs.perplexity.ai/docs/agent-api/models" - }, - "perplexity/anthropic/claude-fable-5-1": { - "litellm_provider": "perplexity", - "mode": "responses", - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "cache_read_input_token_cost": 2.5e-07, - "source": "https://docs.perplexity.ai/docs/agent-api/models" - }, - "perplexity/anthropic/claude-opus-5-5": { - "litellm_provider": "perplexity", - "mode": "responses", - "input_cost_per_token": 4e-06, - "output_cost_per_token": 2e-05, - "cache_read_input_token_cost": 2e-07, - "source": "https://docs.perplexity.ai/docs/agent-api/models" - }, - "perplexity/openai/gpt-6.1-sol": { - "litellm_provider": "perplexity", - "mode": "responses", - "input_cost_per_token": 2e-06, "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token_above_272k_tokens": 4e-06, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "source": "https://docs.perplexity.ai/docs/agent-api/models" - }, - "perplexity/openai/gpt-6-sol": { - "litellm_provider": "perplexity", - "mode": "responses", - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token_above_272k_tokens": 4e-06, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "source": "https://docs.perplexity.ai/docs/agent-api/models" - }, - "perplexity/openai/gpt-6-astra": { - "litellm_provider": "perplexity", - "mode": "responses", - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "cache_read_input_token_cost": 1e-06, - "cache_creation_input_token_cost": 1.25e-05, - "source": "https://docs.perplexity.ai/docs/agent-api/models" - }, - "perplexity/openai/gpt-6-luna": { - "litellm_provider": "perplexity", - "mode": "responses", - "input_cost_per_token": 1e-07, - "output_cost_per_token": 5e-07, - "cache_read_input_token_cost": 1e-08, - "input_cost_per_token_above_272k_tokens": 2e-07, - "output_cost_per_token_above_272k_tokens": 7.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "source": "https://docs.perplexity.ai/docs/agent-api/models" - }, - "perplexity/google/gemini-3.8-flash": { - "litellm_provider": "perplexity", - "mode": "responses", - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 3.75e-06, - "cache_read_input_token_cost": 7.5e-08, - "source": "https://docs.perplexity.ai/docs/agent-api/models" - }, - "perplexity/xai/grok-4.7": { - "litellm_provider": "perplexity", - "mode": "responses", - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token_above_200k_tokens": 4e-06, - "output_cost_per_token_above_200k_tokens": 1.2e-05, - "cache_read_input_token_cost_above_200k_tokens": 1e-06, - "source": "https://docs.perplexity.ai/docs/agent-api/models" - }, - "us-gov.anthropic.claude-sonnet-5-5": { - "bedrock_converse_supports_strict_tools": false, - "bedrock_output_config_effort_ceiling": "xhigh", - "cache_creation_input_token_cost": 3e-06, - "cache_creation_input_token_cost_above_1hr": 4.8e-06, - "cache_read_input_token_cost": 1.2e-07, - "input_cost_per_token": 2.4e-06, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "supports_forced_tool_use": false, - "thinking_always_on": true, - "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", - "supports_adaptive_thinking": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_mid_conversation_system": true, - "supports_native_structured_output": false, - "supports_output_config": true, - "supports_parallel_tool_use_config": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true - }, - "us.anthropic.claude-sonnet-5-5": { - "bedrock_converse_supports_strict_tools": false, - "cache_creation_input_token_cost": 2.75e-06, - "cache_creation_input_token_cost_above_1hr": 4.4e-06, - "cache_read_input_token_cost": 1.1e-07, - "input_cost_per_token": 2.2e-06, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -70788,6 +77082,238 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "bedrock/claude-sonnet-latest": { + "alias_of": "global.anthropic.claude-sonnet-5-5" + }, + "jp.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "perplexity/anthropic/claude-sonnet-5-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_adaptive_thinking": true, + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-fable-5-2": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 8e-06, + "output_cost_per_token": 4e-05, + "cache_read_input_token_cost": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-fable-5-1": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 2.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-opus-5-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 4e-06, + "output_cost_per_token": 2e-05, + "cache_read_input_token_cost": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6.1-sol": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6-sol": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6-astra": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_creation_input_token_cost": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6-luna": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token_above_272k_tokens": 2e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.8-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_sampling_params": false, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "cache_read_input_token_cost": 7.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.7": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "us-gov.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } + }, + "us.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "us.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -70810,7 +77336,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -70837,6 +77362,9 @@ "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, + "vertex_ai/claude-sonnet-latest": { + "alias_of": "vertex_ai/claude-sonnet-5-5" + }, "vertex_ai/claude-sonnet-5-5@default": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, @@ -70850,7 +77378,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -70883,7 +77410,6 @@ "litellm_provider": "prism", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 6.3e-07, "source": "https://prisminference.com/pricing", @@ -70908,7 +77434,6 @@ "litellm_provider": "prism", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.1e-07, "source": "https://prisminference.com/pricing", @@ -70939,20 +77464,22 @@ "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "bedrock_converse", - "max_input_tokens": 500000, - "max_output_tokens": 500000, - "max_tokens": 500000, + "max_input_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_flex": 3e-06, "output_cost_per_token_priority": 1.05e-05, - "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html", "supports_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, + "bedrock/grok-latest": { + "alias_of": "global.xai.grok-4.7" + }, "us.xai.grok-4.7": { "supports_regex_lookaround": false, "supported_endpoints": ["/v1/chat/completions"], @@ -70965,14 +77492,40 @@ "input_cost_per_token_flex": 1.1e-06, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "bedrock_converse", - "max_input_tokens": 500000, - "max_output_tokens": 500000, - "max_tokens": 500000, + "max_input_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 6.6e-06, "output_cost_per_token_flex": 3.3e-06, "output_cost_per_token_priority": 1.155e-05, - "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html", + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us-gov.xai.grok-4.7": { + "supports_regex_lookaround": false, + "supported_endpoints": ["/v1/chat/completions"], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, + "cache_read_input_token_cost": 6.6e-07, + "cache_read_input_token_cost_flex": 3.3e-07, + "cache_read_input_token_cost_priority": 1.155e-06, + "input_cost_per_token": 2.64e-06, + "input_cost_per_token_batches": 1.32e-06, + "input_cost_per_token_flex": 1.32e-06, + "input_cost_per_token_priority": 4.62e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 7.92e-06, + "output_cost_per_token_batches": 3.96e-06, + "output_cost_per_token_flex": 3.96e-06, + "output_cost_per_token_priority": 1.386e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, @@ -70985,7 +77538,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://inference.baseten.co/v1/models", @@ -70998,6 +77550,16 @@ }, "gpt-6.1-sol": { "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_12hr": 5e-06, + "cache_creation_input_token_cost_above_12hr_ultrafast": 3e-05, + "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 6e-05, + "cache_creation_input_token_cost_above_12hr_flex": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_priority": 1e-05, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, @@ -71030,7 +77592,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, @@ -71042,8 +77603,18 @@ "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 2e-05, "output_cost_per_token_ultrafast": 6e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -71076,10 +77647,14 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "gpt-sol-latest": { + "alias_of": "gpt-6.1-sol" + }, "global.openai.gpt-6.1-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, @@ -71097,7 +77672,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, @@ -71127,6 +77701,9 @@ "supports_sampling_params": false, "supports_xhigh_reasoning_effort": true }, + "bedrock/gpt-sol-latest": { + "alias_of": "global.openai.gpt-6.1-sol" + }, "bedrock_mantle/openai.gpt-6.1-sol": { "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, @@ -71143,12 +77720,12 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "responses", "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05, "output_cost_per_token_ultrafast": 6.6e-05, + "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", "supported_endpoints": [ "/v1/chat/completions", @@ -71171,9 +77748,13 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, + "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "use_openai_responses_path": true }, + "bedrock_mantle/gpt-sol-latest": { + "alias_of": "bedrock_mantle/openai.gpt-6.1-sol" + }, "us.openai.gpt-6.1-sol": { "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, @@ -71191,7 +77772,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, @@ -71226,7 +77806,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 9e-06, "output_cost_per_token": 9e-06, @@ -71240,7 +77819,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 6e-06, "output_cost_per_token": 6e-06, @@ -71257,7 +77835,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 524288, "max_output_tokens": 524288, - "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, @@ -71269,13 +77846,17 @@ "supports_tool_choice": true, "supports_vision": true }, + "vertex_ai/grok-latest": { + "alias_of": "vertex_ai/xai/grok-4.7" + }, "azure_ai/kimi-k2-thinking": { "deprecation_date": "2026-03-29", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", + "successor_model": "azure_ai/kimi-k2.5", "input_cost_per_token": 6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", @@ -71286,6 +77867,7 @@ "text" ], "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, @@ -71308,7 +77890,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.28e-06, "output_cost_per_token_batches": 2.64e-06, @@ -71325,6 +77906,9 @@ "supports_tool_choice": true, "supports_vision": false }, + "bedrock/glm-latest": { + "alias_of": "global.zai.glm-5.3" + }, "us.zai.glm-5.3": { "cache_creation_input_token_cost": 2.31e-06, "cache_creation_input_token_cost_batches": 1.155e-06, @@ -71341,7 +77925,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.808e-06, "output_cost_per_token_batches": 2.904e-06, @@ -71362,33 +77945,36 @@ "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 3.3e-07, "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 64000, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2.75e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-2-5-sonic.md", "supports_audio_input": true, "supports_audio_output": true }, "azure/model-router": { "comment": "The flat $0.14 per M input tokens is the router's own fee, the routed model is priced on top of it", "deprecation_date": "2027-05-20", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.4e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/model-router/", "supports_vision": true }, "azure/whisper": { - "deprecation_date": "2026-12-15", + "deprecation_date": "2027-02-26", + "deprecation_source": "https://management.azure.com/subscriptions/a88257a5-3323-4ef9-95bf-5681a46c9624/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", "input_cost_per_second": 0.0001, "litellm_provider": "azure", "mode": "audio_transcription", "output_cost_per_second": 0.0001, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://management.azure.com/subscriptions/a88257a5-3323-4ef9-95bf-5681a46c9624/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01" }, "gemini/gemini-nano-banana-2.1": { "input_cost_per_token": 1.5e-06, @@ -71396,10 +77982,10 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, "rpm": 1000.0, @@ -71430,6 +78016,9 @@ "tpm": 4000000.0, "web_search_billing_unit": "per_query" }, + "gemini/nano-banana-latest": { + "alias_of": "gemini/gemini-nano-banana-2.1" + }, "gemini-nano-banana-2.1": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, @@ -71441,10 +78030,11 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, + "output_cost_per_image_token_priority": 5.4e-05, "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, @@ -71487,10 +78077,11 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, + "output_cost_per_image_token_batches": 1.5e-05, + "output_cost_per_image_token_priority": 5.4e-05, "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, @@ -71522,6 +78113,9 @@ "supports_web_search": true, "web_search_billing_unit": "per_query" }, + "vertex_ai/nano-banana-latest": { + "alias_of": "vertex_ai/gemini-nano-banana-2.1" + }, "azure_ai/grok-4.7": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, @@ -71531,12 +78125,12 @@ "litellm_provider": "azure_ai", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://docs.x.ai/developers/models/grok-4.7", "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -71544,6 +78138,9 @@ "supports_vision": true, "supports_web_search": true }, + "azure_ai/grok-latest": { + "alias_of": "azure_ai/grok-4.7" + }, "in.moonshotai.kimi-k3": { "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_flex": 2.0625e-06, @@ -71555,9 +78152,10 @@ "input_cost_per_token_flex": 1.65e-06, "input_cost_per_token_priority": 5.775e-06, "litellm_provider": "bedrock_converse", + "token_count_framing": 64, + "token_count_tokenizer": "kimi_k3", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_flex": 8.25e-06, @@ -71590,7 +78188,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_batches": 2.5e-07, @@ -71600,6 +78197,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -71629,6 +78227,9 @@ "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, "cache_read_input_token_cost_above_100k_tokens": 5e-08 }, + "claude-haiku-latest": { + "alias_of": "claude-haiku-5-5" + }, "bedrock_mantle/anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5.5e-07, "output_cost_per_token_above_100k_tokens": 2.75e-06, @@ -71644,7 +78245,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-07, "search_context_cost_per_query": { @@ -71653,6 +78253,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -71675,6 +78276,9 @@ "prompt_cache_min_tokens": 512, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html" }, + "bedrock_mantle/claude-haiku-latest": { + "alias_of": "bedrock_mantle/anthropic.claude-haiku-5-5" + }, "bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 6e-07, "output_cost_per_token_above_100k_tokens": 3e-06, @@ -71691,13 +78295,13 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -71714,7 +78318,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html", + "token_count_model": {"model":"anthropic.claude-haiku-5-5","litellm_provider":"bedrock_mantle","region":"us-gov-west-1"} }, "anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5e-07, @@ -71728,10 +78333,14 @@ "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "search_context_cost_per_query": { @@ -71740,6 +78349,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -71753,6 +78363,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -71773,9 +78384,9 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -71789,6 +78400,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -71804,6 +78417,11 @@ "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "au.anthropic.claude-haiku-5-5": { + "token_count_model": { + "model": "au.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + }, "input_cost_per_token_above_100k_tokens": 5.5e-07, "output_cost_per_token_above_100k_tokens": 2.75e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, @@ -71818,7 +78436,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-07, "search_context_cost_per_query": { @@ -71827,6 +78444,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -71840,6 +78458,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -71864,7 +78484,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "search_context_cost_per_query": { @@ -71873,6 +78492,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -71886,10 +78506,14 @@ "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "supports_forced_tool_use": true, + "supports_web_search": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide" }, + "azure_ai/claude-haiku-latest": { + "alias_of": "azure_ai/claude-haiku-5-5" + }, "bedrock/us-gov-east-1/anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 6e-07, "output_cost_per_token_above_100k_tokens": 3e-06, @@ -71906,7 +78530,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_forced_tool_use": true, @@ -71914,12 +78537,14 @@ "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -71947,7 +78572,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_forced_tool_use": true, @@ -71955,12 +78579,14 @@ "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -71970,7 +78596,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-haiku-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "eu.anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5.5e-07, @@ -71987,7 +78618,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-07, "search_context_cost_per_query": { @@ -71996,6 +78626,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -72009,6 +78640,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -72030,10 +78663,14 @@ "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "global.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "search_context_cost_per_query": { @@ -72042,6 +78679,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -72055,6 +78693,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -72064,6 +78704,9 @@ "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, + "bedrock/claude-haiku-latest": { + "alias_of": "global.anthropic.claude-haiku-5-5" + }, "jp.anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5.5e-07, "output_cost_per_token_above_100k_tokens": 2.75e-06, @@ -72079,7 +78722,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-07, "search_context_cost_per_query": { @@ -72088,6 +78730,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -72101,6 +78744,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -72119,6 +78764,9 @@ "input_cost_per_token": 1e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 1e-08, + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "us-gov.anthropic.claude-haiku-5-5": { @@ -72137,7 +78785,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_forced_tool_use": true, @@ -72145,12 +78792,14 @@ "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -72160,7 +78809,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-haiku-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us.anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5.5e-07, @@ -72174,10 +78828,14 @@ "cache_read_input_token_cost": 1.1e-08, "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "us.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-07, "search_context_cost_per_query": { @@ -72186,6 +78844,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -72199,6 +78858,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -72208,262 +78869,22219 @@ "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "vertex_ai/claude-haiku-5-5": { - "input_cost_per_token_above_100k_tokens": 5e-07, - "output_cost_per_token_above_100k_tokens": 2.5e-06, - "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, - "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, - "cache_read_input_token_cost_above_100k_tokens": 5e-08, - "regional_endpoint_uplift_multiplier": 1.1, - "supports_mid_conversation_system": true, - "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_above_1hr": 2e-07, - "cache_creation_input_token_cost_batches": 6.25e-08, - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_batches": 5e-09, - "input_cost_per_token": 1e-07, - "input_cost_per_token_batches": 5e-08, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_batches": 2.5e-07, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_adaptive_thinking": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true, - "supports_forced_tool_use": true, - "thinking_always_on": false, - "prompt_cache_min_tokens": 512, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + "vertex_ai/claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 5e-09, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_batches": 2.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/claude-haiku-latest": { + "alias_of": "vertex_ai/claude-haiku-5-5" + }, + "vertex_ai/claude-haiku-5-5@default": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 5e-09, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_batches": 2.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "microsoft_365_copilot/chat": { + "litellm_provider": "microsoft_365_copilot", + "mode": "chat", + "supports_mid_conversation_system": true, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0 + }, + "us.twelvelabs.pegasus-1-5-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "litellm_provider": "bedrock", + "max_input_tokens": 261120, + "max_output_tokens": 98304, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", + "supports_video_input": true + }, + "global.twelvelabs.pegasus-1-5-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "litellm_provider": "bedrock", + "max_input_tokens": 261120, + "max_output_tokens": 98304, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", + "supports_video_input": true + }, + "twelvelabs.pegasus-1-5-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "litellm_provider": "bedrock", + "max_input_tokens": 261120, + "max_output_tokens": 98304, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", + "supports_video_input": true + }, + "azure_ai/Microsoft-Decision-1": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 32768, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + }, + "gpt-rosalind-discovery": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://developers.openai.com/api/docs/pricing" + }, + "chatgpt/gpt-rosalind-discovery": { + "litellm_provider": "chatgpt", + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/responses" + ] + }, + "azure_ai/Cohere-Embed-V5-Fast": { + "deprecation_date": "2027-01-23", + "input_cost_per_image_token": 4e-07, + "input_cost_per_token": 8e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supported_modalities": [ + "text", + "image" + ], + "supports_embedding_image_input": true + }, + "azure_ai/Cohere-Embed-V5-Pro": { + "deprecation_date": "2027-01-23", + "input_cost_per_image_token": 4e-07, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supported_modalities": [ + "text", + "image" + ], + "supports_embedding_image_input": true + }, + "scaledown/extract": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_response_schema": false, + "supports_system_messages": false, + "supports_vision": false, + "supports_function_calling": false + }, + "scaledown/summarize": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": true, + "supports_vision": false, + "supports_function_calling": false + }, + "scaledown/compress": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": true, + "supports_function_calling": false, + "supports_vision": false + }, + "scaledown/classify": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": false, + "supports_vision": false, + "supports_function_calling": false + }, + "scaledown/decisions": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": false, + "supports_vision": false, + "supports_function_calling": false + }, + "vertex_ai/gemini-robotics-er-2-preview": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-06, + "output_cost_per_token": 5e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "gemini-robotics-er-2-preview": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-06, + "output_cost_per_token": 5e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "gemini/gemini-4-argon": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 1.8e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 1.8e-05, + "prompt_cache_min_tokens": 4096.0, + "rpm": 2000.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_computer_use": true, + "supports_continuation": true, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000.0, + "web_search_billing_unit": "per_query" + }, + "vertex_ai/gemini-4-argon": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 1.8e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token": 2e-06, + "input_cost_per_audio_token_batches": 1e-06, + "input_cost_per_audio_token_priority": 3.6e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 1.8e-05, + "prompt_cache_min_tokens": 6144.0, + "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_computer_use": true, + "supports_continuation": true, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "vertex_ai/gemini-4-argon-cyber-permissive": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token": 4e-06, + "input_cost_per_audio_token_batches": 2e-06, + "input_cost_per_audio_token_priority": 7.2e-06, + "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2e-06, + "input_cost_per_token_flex": 2e-06, + "input_cost_per_token_priority": 7.2e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 2e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, + "output_cost_per_token_flex": 1e-05, + "output_cost_per_token_priority": 3.6e-05, + "prompt_cache_min_tokens": 6144.0, + "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_continuation": true, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "github_copilot/gemini-4-argon": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_vision": true + }, + "openinfer/@oi/GLM-5.3-Flash": { + "max_input_tokens": 393216, + "max_output_tokens": 393216, + "input_cost_per_token": 1.95e-07, + "output_cost_per_token": 1.56e-06, + "litellm_provider": "openinfer", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://api.openinfer.ai/v1/models" + }, + "openinfer/@oi/Qwen3.5-27B": { + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1.95e-07, + "output_cost_per_token": 1.56e-06, + "litellm_provider": "openinfer", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://api.openinfer.ai/v1/models" + }, + "openinfer/@oi/Qwen3.5-9B": { + "max_input_tokens": 100000, + "max_output_tokens": 100000, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "openinfer", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://api.openinfer.ai/v1/models" + }, + "xai/grok-voice-3.0": { + "input_cost_per_second": 0.001333333333333, + "input_cost_per_text_message": 0.004, + "litellm_provider": "xai", + "mode": "realtime", + "source": "https://docs.x.ai/developers/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true + }, + "xai/grok-voice-latest": { + "input_cost_per_second": 0.001333333333333, + "input_cost_per_text_message": 0.004, + "litellm_provider": "xai", + "mode": "realtime", + "source": "https://docs.x.ai/developers/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true + }, + "xai/grok-voice-2.0": { + "input_cost_per_second": 0.001333333333333, + "input_cost_per_text_message": 0.004, + "litellm_provider": "xai", + "mode": "realtime", + "source": "https://docs.x.ai/developers/pricing", + "successor_model": "xai/grok-voice-3.0", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true + }, + "together_ai/nvidia/NVIDIA-Nemotron-3.5-Super-VL": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "jp.amazon.nova-2-lite-v1:0": { + "cache_read_input_token_cost": 9.9e-08, + "cache_read_input_token_cost_flex": 4.95e-08, + "cache_read_input_token_cost_priority": 1.7325e-07, + "input_cost_per_token": 3.96e-07, + "input_cost_per_token_batches": 1.98e-07, + "input_cost_per_token_flex": 1.98e-07, + "input_cost_per_token_priority": 6.93e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.311e-06, + "output_cost_per_token_batches": 1.6555e-06, + "output_cost_per_token_flex": 1.6555e-06, + "output_cost_per_token_priority": 5.79425e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-northeast-1/index.json", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "vertex_ai/deepseek-ai/deepseek-v4.1-flash-maas": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-deepseek_models", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_regions": [ + "global" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/claude-opus-5-5-fast": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-01-15", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "input_cost_per_token": 8e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.02,"search_context_size_low":0.02,"search_context_size_medium":0.02}, + "source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "thinking_always_on": true + }, + "baseten/meta-models/muse-spark-open": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, + "max_output_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "together_ai/reflection/Beam-1.0-501B-A23B": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "baseten/reflection/Beam-1.0": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "nebius/reflection/beam": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://tokenfactory.nebius.com/api/public/models_info", + "supports_function_calling": true, + "supports_reasoning": true, + "cache_read_input_token_cost": 5e-08 + }, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017": { + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_priority": 7.5e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 3.75e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.5e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/deepseek-flash-latest": { + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_priority": 7.5e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 3.75e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.5e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "github_copilot/claude-sonnet-4.6": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-09-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_legacy_thinking": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.4-nano": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.25e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/grok-4.5": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/grok-4.6": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/grok-4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/grok-latest": { + "alias_of": "github_copilot/grok-4.7" + }, + "together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "meta/muse-image-1.0": { + "litellm_provider": "meta", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://dev.meta.ai/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "fireworks_ai/accounts/fireworks/models/minimax-m3p1-flash": { + "cache_read_input_token_cost": 1.5e-08, + "cache_read_input_token_cost_priority": 2.25e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_priority": 2.25e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_priority": 9e-07, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "meta/sam-3.1": { + "input_cost_per_image": 0.0025, + "litellm_provider": "meta", + "mode": "responses", + "source": "https://dev.meta.ai/docs/pricing-rate-limits.md", + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" + ] + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us": { + "cache_read_input_token_cost": 9e-09, + "cache_read_input_token_cost_priority": 1.125e-08, + "input_cost_per_token": 4.5e-07, + "input_cost_per_token_priority": 5.625e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.8e-06, + "output_cost_per_token_priority": 2.25e-06, + "source": "https://docs.fireworks.ai/serverless/us-only-serverless", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "wandb/reflection/Beam-1.0-501B-A23B": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "wandb/zai-org/GLM-5.3": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/MAI-Code-1.1-Flash": { + "cache_read_input_token_cost": 2e-08, + "deprecation_date": "2026-12-09", + "input_cost_per_token": 2e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 256000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "opencode_go/grok-4.7": { + "litellm_provider": "opencode_go", + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 5e-07, + "max_output_tokens": 500000, + "max_input_tokens": 500000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "tiered_pricing": [ + { + "range": [ + 0, + 200000 + ], + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 5e-07 + }, + { + "range": [ + 200000, + 500000 + ], + "input_cost_per_token": 4e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 1e-06 + } + ], + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/gpt-6-luna": { + "litellm_provider": "opencode_go", + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "input_cost_per_token": 1.0000000000000001e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_creation_input_token_cost": 1.25e-07, + "max_output_tokens": 128000, + "max_input_tokens": 922000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "tiered_pricing": [ + { + "range": [ + 0, + 272000 + ], + "input_cost_per_token": 1.0000000000000001e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_creation_input_token_cost": 1.25e-07 + }, + { + "range": [ + 272000, + 1050000 + ], + "input_cost_per_token": 2.0000000000000002e-07, + "output_cost_per_token": 7.5e-07, + "cache_read_input_token_cost": 2e-08, + "cache_creation_input_token_cost": 2.5e-07 + } + ], + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/gpt-5.6-luna": { + "litellm_provider": "opencode_go", + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "input_cost_per_token": 2.0000000000000002e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 2e-08, + "cache_creation_input_token_cost": 2.5e-07, + "max_output_tokens": 128000, + "max_input_tokens": 922000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "tiered_pricing": [ + { + "range": [ + 0, + 272000 + ], + "input_cost_per_token": 2.0000000000000002e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 2e-08, + "cache_creation_input_token_cost": 2.5e-07 + }, + { + "range": [ + 272000, + 1050000 + ], + "input_cost_per_token": 4.0000000000000003e-07, + "output_cost_per_token": 1.8000000000000001e-06, + "cache_read_input_token_cost": 4e-08, + "cache_creation_input_token_cost": 5e-07 + } + ], + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/claude-haiku-5-5": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/messages" + ], + "input_cost_per_token": 1.0000000000000001e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_creation_input_token_cost": 1.25e-07, + "max_output_tokens": 128000, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "tiered_pricing": [ + { + "range": [ + 0, + 100000 + ], + "input_cost_per_token": 1.0000000000000001e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_creation_input_token_cost": 1.25e-07 + }, + { + "range": [ + 100000, + 1000000 + ], + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 5.0000000000000004e-08, + "cache_creation_input_token_cost": 6.25e-07 + } + ], + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/gemini-4-argon": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1beta/models" + ], + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1e-07, + "max_output_tokens": 65536, + "max_input_tokens": 1048576, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/glm-5.3-flash": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 3e-08, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/glm-5.3": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 2.6e-07, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/glm-5.2": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 2.6e-07, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/kimi-k3.1-pro": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2.0000000000000002e-07, + "cache_creation_input_token_cost": 2e-06, + "max_output_tokens": 131072, + "max_input_tokens": 1048576, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/kimi-k3": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3e-06, + "max_output_tokens": 131072, + "max_input_tokens": 1048576, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/kimi-k2.7-code": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 9.499999999999999e-07, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 1.9e-07, + "max_output_tokens": 262144, + "max_input_tokens": 262144, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/longcat-2.0": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 6e-09, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/deepseek-v4.1-flash": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 6e-09, + "max_output_tokens": 384000, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/deepseek-v4-pro": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.32e-06, + "output_cost_per_token": 3.96e-06, + "cache_read_input_token_cost": 4.4e-08, + "max_output_tokens": 384000, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/mimo-v2.6-flash": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 2.8e-09, + "max_output_tokens": 131072, + "max_input_tokens": 1048576, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/mimo-v2.6-pro": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 4.35e-07, + "output_cost_per_token": 8.7e-07, + "cache_read_input_token_cost": 3.625e-09, + "max_output_tokens": 131072, + "max_input_tokens": 1048576, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/mimo-v2.5": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 2.8e-09, + "max_output_tokens": 128000, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/mimo-v2.5-pro": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 4.35e-07, + "output_cost_per_token": 8.7e-07, + "cache_read_input_token_cost": 3.625e-09, + "max_output_tokens": 128000, + "max_input_tokens": 1048576, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/minimax-m3.1-flash": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 1.5e-08, + "max_output_tokens": 512000, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/minimax-m3": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/messages" + ], + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 6e-08, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/muse-spark-1.3-contributor": { + "litellm_provider": "opencode_go", + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "input_cost_per_token": 1.0000000000000001e-07, + "output_cost_per_token": 2.0000000000000002e-07, + "cache_read_input_token_cost": 2e-09, + "max_output_tokens": 131072, + "max_input_tokens": 1048576, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/muse-spark-1.2-contributor": { + "litellm_provider": "opencode_go", + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "input_cost_per_token": 1.0000000000000001e-07, + "output_cost_per_token": 2.0000000000000002e-07, + "cache_read_input_token_cost": 2e-09, + "max_output_tokens": 131072, + "max_input_tokens": 1048576, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/qwen3.8-max": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/messages" + ], + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost": 2.5e-06, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/qwen3.8-flash": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/messages" + ], + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 4.6999999999999995e-07, + "cache_read_input_token_cost": 1.6e-08, + "cache_creation_input_token_cost": 2.0000000000000002e-07, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/qwen3.7-plus": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/messages" + ], + "input_cost_per_token": 4.0000000000000003e-07, + "output_cost_per_token": 1.6000000000000001e-06, + "cache_read_input_token_cost": 4e-08, + "cache_creation_input_token_cost": 5e-07, + "max_output_tokens": 65536, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "tiered_pricing": [ + { + "range": [ + 0, + 256000 + ], + "input_cost_per_token": 4.0000000000000003e-07, + "output_cost_per_token": 1.6000000000000001e-06, + "cache_read_input_token_cost": 4e-08, + "cache_creation_input_token_cost": 5e-07 + }, + { + "range": [ + 256000, + 1000000 + ], + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 4.8e-06, + "cache_read_input_token_cost": 1.2e-07, + "cache_creation_input_token_cost": 1.5e-06 + } + ], + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/hy4-preview": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 8.34e-07, + "output_cost_per_token": 2.501e-06, + "cache_read_input_token_cost": 4.2000000000000006e-08, + "max_output_tokens": 64000, + "max_input_tokens": 1024000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/hy3": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 5.8e-07, + "cache_read_input_token_cost": 3.5e-08, + "max_output_tokens": 128000, + "max_input_tokens": 192000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/longcat-2.5-preview-free": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "cache_read_input_token_cost": 0, + "max_output_tokens": 131072, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/step-5-preview": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 1e-06, + "output_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 1.0000000000000001e-07, + "max_output_tokens": 65536, + "max_input_tokens": 1000000, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "opencode_go/beam-free": { + "litellm_provider": "opencode_go", + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "cache_read_input_token_cost": 0, + "max_output_tokens": 131072, + "max_input_tokens": 1048576, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://opencode.ai/v2/docs/console/go/" + }, + "bedrock/claude_platform/claude-fable-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-fable-5-1": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-haiku-4-5": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_computer_use": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens_batches": 2.5e-07, + "output_cost_per_token_above_100k_tokens_batches": 1.25e-06, + "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07, + "cache_read_input_token_cost_above_100k_tokens_batches": 2.5e-08, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 5e-09, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_batches": 2.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing", + "supports_web_search": true, + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08 + }, + "bedrock/claude_platform/claude-opus-4-5": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_output_config": true, + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-4-6": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-4-7": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 2048, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-4-8": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-opus-5-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_creation_input_token_cost_batches": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-sonnet-4-5": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, + "cache_read_input_token_cost_batches": 1.5e-07, + "deprecation_date": "2026-11-30", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", + "successor_model": "bedrock/claude_platform/claude-sonnet-5-5", + "input_cost_per_token_batches": 1.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-sonnet-4-6": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_output_config": true, + "prompt_cache_min_tokens": 1024, + "provider_specific_entry": { + "us": 1.1 + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-sonnet-5": { + "supports_web_search": true, + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" + }, + "bedrock/claude_platform/claude-sonnet-5-5": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing", + "supports_web_search": true + }, + "gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_12hr": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_above_12hr_batches": 1.25e-06, + "cache_creation_input_token_cost_above_12hr_flex": 1.25e-06, + "cache_creation_input_token_cost_above_12hr_priority": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, + "cache_creation_input_token_cost_flex": 6.25e-07, + "cache_creation_input_token_cost_priority": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 5e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-07, + "cache_read_input_token_cost_batches": 2.5e-08, + "cache_read_input_token_cost_flex": 2.5e-08, + "cache_read_input_token_cost_priority": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "input_cost_per_token_above_272k_tokens_batches": 1e-06, + "input_cost_per_token_above_272k_tokens_flex": 1e-06, + "input_cost_per_token_above_272k_tokens_priority": 4e-06, + "input_cost_per_token_batches": 5e-07, + "input_cost_per_token_flex": 5e-07, + "input_cost_per_token_priority": 2e-06, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 3.75e-06, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-06, + "output_cost_per_token_above_272k_tokens_priority": 1.5e-05, + "output_cost_per_token_batches": 2.5e-06, + "output_cost_per_token_flex": 2.5e-06, + "output_cost_per_token_priority": 1e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "gpt-terra-latest": { + "alias_of": "gpt-6.1-terra" + }, + "chatgpt/gpt-6.1-terra": { + "litellm_provider": "chatgpt", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "global.openai.gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://developers.openai.com/api/docs/models/gpt-6.1-terra", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_bedrock_converse_tool_result_images": false, + "supports_bedrock_runtime_chat_completions_response_format": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "bedrock/gpt-terra-latest": { + "alias_of": "global.openai.gpt-6.1-terra" + }, + "us.openai.gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.375e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-06, + "cache_read_input_token_cost": 5.5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_above_272k_tokens": 2.2e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-06, + "output_cost_per_token_above_272k_tokens": 8.25e-06, + "source": "https://developers.openai.com/api/docs/models/gpt-6.1-terra", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_bedrock_converse_tool_result_images": false, + "supports_bedrock_runtime_chat_completions_response_format": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "baseten/decision-models/baseten-elephant-9b-latest": { + "input_cost_per_token": 3.5e-08, + "litellm_provider": "baseten", + "max_input_tokens": 16384, + "mode": "decisions", + "output_cost_per_token": 0.0, + "source": "https://inference.baseten.co/v1/models", + "supports_vision": true + }, + "baseten/decision-models/baseten-mammoth-27b-latest": { + "input_cost_per_token": 1e-07, + "litellm_provider": "baseten", + "max_input_tokens": 16384, + "mode": "decisions", + "output_cost_per_token": 0.0, + "source": "https://inference.baseten.co/v1/models", + "supports_vision": true + }, + "github_copilot/gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://github.blog/changelog/2026-10-26-gpt-6-1-terra-in-github-copilot", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-terra-latest": { + "alias_of": "github_copilot/gpt-6.1-terra" + }, + "refuseless/glm-5.3-abliterated": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "refuseless", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://refuseless.com/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ] + }, + "refuseless/glm-5.3-flash-abliterated": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "refuseless", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://refuseless.com/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ] + }, + "refuseless/deepseek-v4.1-flash-abliterated": { + "cache_read_input_token_cost": 3.5e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "refuseless", + "max_input_tokens": 1048576, + "max_output_tokens": 130000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://refuseless.com/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ] + }, + "refuseless/deepseek-v4.1-flash-fast": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "refuseless", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://refuseless.com/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ] + }, + "refuseless/minimax-m3.1-flash": { + "cache_read_input_token_cost": 2e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "refuseless", + "max_input_tokens": 1048576, + "max_output_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://refuseless.com/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ] + }, + "fireworks_ai/accounts/fireworks/models/rune": { + "cache_read_input_token_cost": 8.4e-09, + "input_cost_per_token": 4.2e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "mode": "decisions", + "output_cost_per_token": 0.0, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested" + }, + "bedrock_mantle/openai.gpt-6.1-terra": { + "cache_creation_input_token_cost": 1.375e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-06, + "cache_read_input_token_cost": 5.5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_above_272k_tokens": 2.2e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 5.5e-06, + "output_cost_per_token_above_272k_tokens": 8.25e-06, + "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-terra.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true, + "use_openai_responses_path": true + }, + "bedrock_mantle/gpt-terra-latest": { + "alias_of": "bedrock_mantle/openai.gpt-6.1-terra" + }, + "clf_ai_gateway/glm-5.3": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 5.6e-07, + "output_cost_per_token": 1.76e-06, + "cache_read_input_token_cost": 1.04e-07, + "litellm_provider": "clf_ai_gateway", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "max" + ], + "supports_response_schema": true, + "supports_system_messages": true, + "supports_prompt_caching": true, + "source": "https://clfaigateway.dev/models" + }, + "clf_ai_gateway/glm-5.3-flash": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2e-07, + "cache_read_input_token_cost": 1.2e-08, + "litellm_provider": "clf_ai_gateway", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "xhigh", + "max" + ], + "supports_response_schema": true, + "supports_system_messages": true, + "supports_prompt_caching": true, + "supports_vision": true, + "source": "https://clfaigateway.dev/models" + }, + "clf_ai_gateway/glm-5.2": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 5.6e-07, + "output_cost_per_token": 1.76e-06, + "cache_read_input_token_cost": 1.04e-07, + "litellm_provider": "clf_ai_gateway", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "xhigh", + "max" + ], + "supports_response_schema": true, + "supports_system_messages": true, + "supports_prompt_caching": true, + "source": "https://clfaigateway.dev/models" + }, + "clf_ai_gateway/glm-4.7-flash": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2.4e-08, + "output_cost_per_token": 1.6e-07, + "litellm_provider": "clf_ai_gateway", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high" + ], + "supports_response_schema": true, + "supports_system_messages": true, + "source": "https://clfaigateway.dev/models" + }, + "clf_ai_gateway/deepseek-v4-pro": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 5.28e-07, + "output_cost_per_token": 1.584e-06, + "cache_read_input_token_cost": 1.7e-08, + "litellm_provider": "clf_ai_gateway", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "xhigh", + "max" + ], + "supports_response_schema": true, + "supports_system_messages": true, + "supports_prompt_caching": true, + "source": "https://clfaigateway.dev/models" + }, + "clf_ai_gateway/deepseek-v4-flash": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.76e-07, + "output_cost_per_token": 5.28e-07, + "cache_read_input_token_cost": 5e-09, + "litellm_provider": "clf_ai_gateway", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "xhigh", + "max" + ], + "supports_response_schema": true, + "supports_system_messages": true, + "supports_prompt_caching": true, + "source": "https://clfaigateway.dev/models" + }, + "clf_ai_gateway/deepseek-v4.1-flash": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 4.8e-07, + "cache_read_input_token_cost": 2e-09, + "litellm_provider": "clf_ai_gateway", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "supports_response_schema": true, + "supports_system_messages": true, + "supports_prompt_caching": true, + "supports_vision": true, + "source": "https://clfaigateway.dev/models" + }, + "clf_ai_gateway/kimi-k2.6": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 1.6e-06, + "cache_read_input_token_cost": 6.4e-08, + "litellm_provider": "clf_ai_gateway", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high" + ], + "supports_response_schema": true, + "supports_system_messages": true, + "supports_prompt_caching": true, + "supports_vision": true, + "source": "https://clfaigateway.dev/models" + }, + "clf_ai_gateway/kimi-k2.7-code": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 1.6e-06, + "cache_read_input_token_cost": 7.6e-08, + "litellm_provider": "clf_ai_gateway", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high" + ], + "supports_response_schema": true, + "supports_system_messages": true, + "supports_prompt_caching": true, + "supports_vision": true, + "source": "https://clfaigateway.dev/models" + }, + "clf_ai_gateway/qwen3.8-27b": { + "metadata": { + "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." + }, + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 1.8e-07, + "output_cost_per_token": 1.28e-06, + "cache_read_input_token_cost": 2e-08, + "litellm_provider": "clf_ai_gateway", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "medium", + "xhigh" + ], + "supports_response_schema": true, + "supports_system_messages": true, + "supports_prompt_caching": true, + "supports_vision": true, + "source": "https://clfaigateway.dev/models" + }, + "kyma/claude-fable-5": { + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.35e-05, + "output_cost_per_token": 6.75e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true, + "supports_adaptive_thinking": true, + "thinking_always_on": true + }, + "kyma/claude-fable-5.1": { + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.35e-05, + "output_cost_per_token": 6.75e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true, + "supports_adaptive_thinking": true, + "thinking_always_on": true + }, + "kyma/claude-haiku-4-5": { + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "input_cost_per_token": 1.35e-06, + "cache_read_input_token_cost": 1.35e-07, + "output_cost_per_token": 6.75e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false, + "prompt_cache_min_tokens": 4096 + }, + "kyma/claude-haiku-5.5": { + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.35e-07, + "cache_read_input_token_cost": 1.35e-08, + "output_cost_per_token": 6.75e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true, + "supports_adaptive_thinking": true, + "thinking_always_on": false, + "prompt_cache_min_tokens": 512 + }, + "kyma/claude-opus-4-7": { + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "input_cost_per_token": 6.75e-06, + "cache_read_input_token_cost": 6.75e-07, + "output_cost_per_token": 3.375e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false, + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 2048 + }, + "kyma/claude-opus-5": { + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "input_cost_per_token": 6.75e-06, + "cache_read_input_token_cost": 6.75e-07, + "output_cost_per_token": 3.375e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true, + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 512 + }, + "kyma/claude-opus-5.5": { + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "input_cost_per_token": 5.4e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 2.7e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512 + }, + "kyma/claude-sonnet-4-6": { + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "input_cost_per_token": 4.05e-06, + "cache_read_input_token_cost": 4.05e-07, + "output_cost_per_token": 2.025e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false, + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 1024 + }, + "kyma/claude-sonnet-5": { + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 1.35e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true, + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 1024 + }, + "kyma/claude-sonnet-5.5": { + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 1.35e-07, + "output_cost_per_token": 1.35e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512 + }, + "kyma/deepseek-r1": { + "max_input_tokens": 64000, + "max_output_tokens": 32768, + "input_cost_per_token": 7.425e-07, + "output_cost_per_token": 2.957e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/deepseek-v3": { + "max_input_tokens": 160000, + "max_output_tokens": 8192, + "input_cost_per_token": 5.18e-07, + "output_cost_per_token": 7.571e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/deepseek-v4-flash": { + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "input_cost_per_token": 1.23e-07, + "cache_read_input_token_cost": 2.43e-08, + "output_cost_per_token": 2.458e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/deepseek-v4-flash-vision-exp": { + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "input_cost_per_token": 3.892e-07, + "output_cost_per_token": 1.168e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/deepseek-v4.1-flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 8.1e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/gemini-3-flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "input_cost_per_token": 6.75e-07, + "cache_read_input_token_cost": 6.75e-08, + "output_cost_per_token": 4.05e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/gemini-3.1-pro": { + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 1.62e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/gemini-3.5-flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "input_cost_per_token": 2.025e-06, + "cache_read_input_token_cost": 2.025e-07, + "output_cost_per_token": 1.215e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/gemini-3.5-flash-lite": { + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "input_cost_per_token": 4.05e-07, + "cache_read_input_token_cost": 4.05e-08, + "output_cost_per_token": 3.375e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/gemini-3.6-flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "input_cost_per_token": 1.013e-06, + "cache_read_input_token_cost": 1.0125e-07, + "output_cost_per_token": 5.063e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_pdf_input": false + }, + "kyma/gemini-3.7-flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "input_cost_per_token": 2.026e-06, + "cache_read_input_token_cost": 1.0125e-07, + "output_cost_per_token": 1.0126e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/gemini-3.8-flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "input_cost_per_token": 2.026e-06, + "output_cost_per_token": 1.0126e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/gemini-4-argon": { + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "input_cost_per_token": 5.4e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 2.7e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/gemma-4-31b": { + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "input_cost_per_token": 1.642e-07, + "cache_read_input_token_cost": 1.642e-07, + "output_cost_per_token": 4.689e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/glm-4.5-air": { + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "input_cost_per_token": 1.797e-07, + "cache_read_input_token_cost": 3.375e-08, + "output_cost_per_token": 1.175e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/glm-4.7-flash": { + "max_input_tokens": 203000, + "max_output_tokens": 65536, + "input_cost_per_token": 8.1e-08, + "cache_read_input_token_cost": 1.35e-08, + "output_cost_per_token": 5.4e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/glm-5.1": { + "max_input_tokens": 203000, + "max_output_tokens": 65536, + "input_cost_per_token": 1.89e-06, + "cache_read_input_token_cost": 2.7675e-07, + "output_cost_per_token": 5.94e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/glm-5.2": { + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 9.029e-07, + "cache_read_input_token_cost": 2.9835e-07, + "output_cost_per_token": 3.083e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/glm-5.3": { + "max_input_tokens": 1310720, + "max_output_tokens": 131072, + "input_cost_per_token": 1.178e-06, + "output_cost_per_token": 3.702e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/glm-5.3-flash": { + "max_input_tokens": 1310720, + "max_output_tokens": 65536, + "input_cost_per_token": 1.72e-07, + "output_cost_per_token": 5.733e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/gpt-5.6-luna": { + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 2.944e-07, + "cache_read_input_token_cost": 2.7e-08, + "output_cost_per_token": 1.767e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/gpt-5.6-luna-pro": { + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 2.703e-07, + "cache_read_input_token_cost": 2.7e-08, + "output_cost_per_token": 1.621e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/gpt-5.6-sol": { + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 5.4e-06, + "cache_read_input_token_cost": 6.75e-07, + "output_cost_per_token": 2.7e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/gpt-5.6-sol-pro": { + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 5.4e-06, + "cache_read_input_token_cost": 6.75e-07, + "output_cost_per_token": 2.7e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/gpt-5.6-terra": { + "max_input_tokens": 1050000, + "max_output_tokens": 8192, + "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 1.62e-05, + "input_cost_per_token_above_272k_tokens": 5.4e-06, + "output_cost_per_token_above_272k_tokens": 2.43e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/gpt-5.6-terra-pro": { + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 1.62e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/gpt-6-astra": { + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.35e-05, + "cache_read_input_token_cost": 1.35e-06, + "output_cost_per_token": 6.75e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/gpt-6-luna": { + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.639e-07, + "cache_read_input_token_cost": 1.35e-08, + "output_cost_per_token": 8.195e-07, + "input_cost_per_token_above_272k_tokens": 2.7e-07, + "output_cost_per_token_above_272k_tokens": 1.0125e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/gpt-6.1-sol": { + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 1.35e-07, + "output_cost_per_token": 1.35e-05, + "input_cost_per_token_above_272k_tokens": 5.4e-06, + "output_cost_per_token_above_272k_tokens": 2.025e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/gpt-oss-120b": { + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "input_cost_per_token": 4.73e-08, + "output_cost_per_token": 2.303e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/grok-4.20": { + "max_input_tokens": 2000000, + "max_output_tokens": 8192, + "input_cost_per_token": 1.763e-06, + "output_cost_per_token": 3.528e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/grok-4.20-multi-agent": { + "max_input_tokens": 2000000, + "max_output_tokens": 8192, + "input_cost_per_token": 1.767e-06, + "output_cost_per_token": 3.534e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": false, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/grok-4.3": { + "max_input_tokens": 1000000, + "max_output_tokens": 32768, + "input_cost_per_token": 1.92e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 3.838e-06, + "input_cost_per_token_above_200k_tokens": 3.375e-06, + "output_cost_per_token_above_200k_tokens": 6.75e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/grok-4.5": { + "max_input_tokens": 500000, + "max_output_tokens": 8192, + "input_cost_per_token": 2.73e-06, + "output_cost_per_token": 8.189e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/grok-4.6": { + "max_input_tokens": 500000, + "max_output_tokens": 8192, + "input_cost_per_token": 2.758e-06, + "output_cost_per_token": 8.274e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/grok-4.7": { + "max_input_tokens": 500000, + "max_output_tokens": 450000, + "input_cost_per_token": 2.16e-06, + "cache_read_input_token_cost": 5.4e-07, + "output_cost_per_token": 6.48e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/grok-build": { + "max_input_tokens": 256000, + "max_output_tokens": 32768, + "input_cost_per_token": 1.389e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 2.777e-06, + "input_cost_per_token_above_200k_tokens": 2.7e-06, + "output_cost_per_token_above_200k_tokens": 5.4e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/hy3": { + "max_input_tokens": 262144, + "max_output_tokens": 8192, + "input_cost_per_token": 1.594e-07, + "output_cost_per_token": 6.576e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/hy4-preview": { + "max_input_tokens": 1048576, + "max_output_tokens": 64000, + "input_cost_per_token": 1.1259e-06, + "output_cost_per_token": 3.3764e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/kimi-k2.6": { + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "input_cost_per_token": 5.909e-07, + "output_cost_per_token": 2.758e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/kimi-k2.7-code": { + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "input_cost_per_token": 1.009e-06, + "output_cost_per_token": 4.774e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/kimi-k3": { + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "input_cost_per_token": 3.052e-06, + "cache_read_input_token_cost": 4.05e-07, + "output_cost_per_token": 1.5258e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/kimi-k3.1-pro": { + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "input_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 2.7e-07, + "output_cost_per_token": 1.35e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/llama-3.3-70b": { + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "input_cost_per_token": 1.35e-07, + "output_cost_per_token": 4.32e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/llama-4-maverick": { + "max_input_tokens": 1048576, + "max_output_tokens": 16384, + "input_cost_per_token": 3.344e-07, + "output_cost_per_token": 1.337e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/mimo-v2.5": { + "max_input_tokens": 1050000, + "max_output_tokens": 16384, + "input_cost_per_token": 1.859e-07, + "output_cost_per_token": 3.718e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/mimo-v2.6-flash": { + "max_input_tokens": 1050000, + "max_output_tokens": 131072, + "input_cost_per_token": 1.89e-07, + "output_cost_per_token": 3.78e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/mimo-v2.6-pro": { + "max_input_tokens": 1050000, + "max_output_tokens": 131072, + "input_cost_per_token": 5.805e-07, + "output_cost_per_token": 1.1745e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/minimax-m2.5": { + "max_input_tokens": 196608, + "max_output_tokens": 32768, + "input_cost_per_token": 4.188e-07, + "output_cost_per_token": 1.675e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/minimax-m2.7": { + "max_input_tokens": 204800, + "max_output_tokens": 32768, + "input_cost_per_token": 4.05e-07, + "output_cost_per_token": 1.62e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/minimax-m3": { + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "input_cost_per_token": 3.956e-07, + "cache_read_input_token_cost": 7.56e-08, + "output_cost_per_token": 1.582e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/minimax-m3.1-flash": { + "max_input_tokens": 1048576, + "max_output_tokens": 524288, + "input_cost_per_token": 2.025e-07, + "cache_read_input_token_cost": 2.025e-08, + "output_cost_per_token": 8.1e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/muse-glimmer-30b": { + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "input_cost_per_token": 4.554e-07, + "output_cost_per_token": 1.821e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/muse-spark-1.1": { + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "input_cost_per_token": 1.542e-06, + "output_cost_per_token": 5.243e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/muse-spark-1.2": { + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "input_cost_per_token": 1.773e-06, + "output_cost_per_token": 6.025e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/muse-spark-1.3": { + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "input_cost_per_token": 1.688e-06, + "output_cost_per_token": 5.738e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/muse-spark-open": { + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "input_cost_per_token": 1.688e-06, + "output_cost_per_token": 5.738e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/muse-wonder": { + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "input_cost_per_token": 5.4e-06, + "output_cost_per_token": 2.7e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": true + }, + "kyma/nemotron-3-ultra-550b": { + "max_input_tokens": 1000000, + "max_output_tokens": 32768, + "input_cost_per_token": 6.75e-07, + "cache_read_input_token_cost": 1.35e-07, + "output_cost_per_token": 3.375e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/nemotron-3.5-super-vl": { + "max_input_tokens": 1048576, + "max_output_tokens": 235929, + "input_cost_per_token": 8.1e-08, + "cache_read_input_token_cost": 1.35e-08, + "output_cost_per_token": 4.725e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/qwen-3-32b": { + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "input_cost_per_token": 1.08e-07, + "output_cost_per_token": 3.78e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/qwen-3-coder": { + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "input_cost_per_token": 3.546e-07, + "cache_read_input_token_cost": 1.35e-07, + "output_cost_per_token": 1.612e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/qwen-3.6-plus": { + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "input_cost_per_token": 4.388e-07, + "output_cost_per_token": 2.633e-06, + "input_cost_per_token_above_256k_tokens": 1.755e-06, + "output_cost_per_token_above_256k_tokens": 5.265e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/qwen-3.7-max": { + "max_input_tokens": 1000000, + "max_output_tokens": 32768, + "input_cost_per_token": 2.071e-06, + "cache_read_input_token_cost": 1.6875e-07, + "output_cost_per_token": 6.207e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/qwen-3.7-plus": { + "max_input_tokens": 1000000, + "max_output_tokens": 32768, + "input_cost_per_token": 4.325e-07, + "cache_read_input_token_cost": 8.64e-08, + "output_cost_per_token": 1.731e-06, + "input_cost_per_token_above_256k_tokens": 1.296e-06, + "output_cost_per_token_above_256k_tokens": 5.184e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/qwen-3.8-max": { + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 2.228e-06, + "cache_read_input_token_cost": 2.781e-07, + "output_cost_per_token": 6.684e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/qwen3.7-flash": { + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "input_cost_per_token": 4.35e-08, + "cache_read_input_token_cost": 8.1e-09, + "output_cost_per_token": 1.886e-07, + "input_cost_per_token_above_32k_tokens": 1.35e-07, + "output_cost_per_token_above_32k_tokens": 5.4e-07, + "input_cost_per_token_above_256k_tokens": 2.7e-07, + "output_cost_per_token_above_256k_tokens": 1.08e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/qwen3.8-27b": { + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 3.826e-07, + "output_cost_per_token": 2.732e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/qwen3.8-flash": { + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 2.045e-07, + "output_cost_per_token": 6.41e-07, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/sonar": { + "max_input_tokens": 127072, + "max_output_tokens": 4096, + "input_cost_per_token": 1.35e-06, + "output_cost_per_token": 1.35e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": false, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_pdf_input": false + }, + "kyma/sonar-pro": { + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "input_cost_per_token": 4.05e-06, + "output_cost_per_token": 2.025e-05, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": false, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_pdf_input": false + }, + "kyma/step-3.7-flash": { + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "input_cost_per_token": 2.229e-07, + "cache_read_input_token_cost": 5.4e-08, + "output_cost_per_token": 1.282e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "kyma/step-5-preview": { + "max_input_tokens": 1048576, + "max_output_tokens": 64000, + "input_cost_per_token": 1.35e-06, + "cache_read_input_token_cost": 1.35e-07, + "output_cost_per_token": 3.645e-06, + "litellm_provider": "kyma", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_pdf_input": false + }, + "databricks/databricks-claude-haiku-5-5": { + "cache_creation_input_token_cost": 1.2502e-07, + "cache_creation_input_token_cost_above_100k_tokens": 6.2503e-07, + "cache_creation_input_token_cost_above_1hr": 1.9999e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.00002e-06, + "cache_read_input_token_cost": 1.001e-08, + "cache_read_input_token_cost_above_100k_tokens": 4.998e-08, + "input_cost_per_token": 1.0003e-07, + "input_cost_per_token_above_100k_tokens": 5.0001e-07, + "input_dbu_cost_per_token": 1.429e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.0001e-07, + "output_cost_per_token_above_100k_tokens": 2.49998e-06, + "output_dbu_cost_per_token": 7.143e-06, + "prompt_cache_min_tokens": 512.0, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "thinking_on_by_default": true, + "supports_anthropic_thinking_payload": true, + "supports_assistant_prefill": false, + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": false + }, + "databricks/claude-haiku-latest": { + "alias_of": "databricks/databricks-claude-haiku-5-5" + }, + "databricks/databricks-claude-sonnet-5-5": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_creation_input_token_cost_above_1hr": 4.00001e-06, + "cache_read_input_token_cost": 1.0003e-07, + "input_cost_per_token": 1.99997e-06, + "input_dbu_cost_per_token": 2.8571e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 9.99999e-06, + "output_dbu_cost_per_token": 0.00014286, + "prompt_cache_min_tokens": 512.0, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_anthropic_thinking_payload": true, + "supports_assistant_prefill": false, + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": false, + "thinking_always_on": true + }, + "databricks/claude-sonnet-latest": { + "alias_of": "databricks/databricks-claude-sonnet-5-5" + }, + "databricks/databricks-deepseek-v4-1-flash": { + "cache_creation_input_token_cost": 3.0002e-07, + "cache_read_input_token_cost": 3.003e-08, + "deprecation_date": "2026-11-19", + "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "input_cost_per_token": 3.0002e-07, + "input_dbu_cost_per_token": 4.286e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. The docs list only databricks-deepseek-v4-1-flash (retiring 2026-11-19) and databricks-deepseek-v4-1-flash-1017, so the pricing page's 'DeepSeek V4.1 Flash (0910)' row prices the unsuffixed endpoint." + }, + "mode": "chat", + "output_cost_per_token": 1.20001e-06, + "output_dbu_cost_per_token": 1.7143e-05, + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "input_cost_per_token_priority": 5.25e-07, + "output_cost_per_token_priority": 2.1e-06, + "cache_read_input_token_cost_priority": 5.25e-08, + "cache_creation_input_token_cost_priority": 5.25e-07, + "successor_model": "databricks/databricks-deepseek-v4-1-flash-1017" + }, + "databricks/databricks-deepseek-v4-1-flash-1017": { + "cache_creation_input_token_cost": 3.0002e-07, + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 3.0002e-07, + "input_dbu_cost_per_token": 4.286e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.20001e-06, + "output_dbu_cost_per_token": 1.7143e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-2-5-flash-lite": { + "cache_creation_input_token_cost": 1.2502e-07, + "cache_read_input_audio_token_cost": 3.752e-08, + "cache_read_input_token_cost": 1.253e-08, + "input_cost_per_audio_token": 3.7499e-07, + "input_cost_per_image_token": 1.2502e-07, + "input_cost_per_token": 1.2502e-07, + "input_dbu_cost_per_token": 1.786e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.0001e-07, + "output_dbu_cost_per_token": 7.143e-06, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-1-flash-lite-image": { + "cache_creation_input_token_cost": 3.1248e-07, + "cache_read_input_token_cost": 3.1248e-07, + "input_cost_per_image_token": 3.1248e-07, + "input_cost_per_token": 3.1248e-07, + "input_dbu_cost_per_token": 4.464e-06, + "litellm_provider": "databricks", + "max_input_tokens": 65536, + "max_output_tokens": 4096, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_image_token": 3.749998e-05, + "output_cost_per_token": 1.87502e-06, + "output_dbu_cost_per_token": 2.6786e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_vision": true + }, + "databricks/databricks-gemini-4-argon": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 1.2502e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.249997e-05, + "output_dbu_cost_per_token": 0.00017857, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "input_cost_per_token_priority": 4.50002e-06, + "output_cost_per_token_priority": 2.250003e-05, + "cache_read_input_token_cost_priority": 2.2498e-07, + "cache_creation_input_token_cost_priority": 4.50002e-06 + }, + "databricks/databricks-gpt-5-4-pro": { + "cache_creation_input_token_cost": 2.999997e-05, + "cache_read_input_token_cost": 2.999997e-05, + "input_cost_per_token": 2.999997e-05, + "input_cost_per_token_above_272k_tokens": 6e-05, + "input_dbu_cost_per_token": 0.00042857, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 0.0001800001, + "output_cost_per_token_above_272k_tokens": 0.00027, + "output_dbu_cost_per_token": 0.0025714, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-6-1-sol": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.00003e-06, + "cache_read_input_token_cost": 1.0003e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.9999e-07, + "input_cost_per_token": 1.99997e-06, + "input_cost_per_token_above_272k_tokens": 4.00001e-06, + "input_dbu_cost_per_token": 2.8571e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 9.99999e-06, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_dbu_cost_per_token": 0.00014286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "input_cost_per_token_priority": 4.00001e-06, + "output_cost_per_token_priority": 1.99997e-05, + "cache_read_input_token_cost_priority": 1.9999e-07, + "cache_creation_input_token_cost_priority": 5.00003e-06, + "input_cost_per_token_above_272k_tokens_priority": 8.00002e-06, + "output_cost_per_token_above_272k_tokens_priority": 2.99999e-05, + "cache_read_input_token_cost_above_272k_tokens_priority": 3.9998e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 9.99999e-06 + }, + "databricks/gpt-sol-latest": { + "alias_of": "databricks/databricks-gpt-6-1-sol" + }, + "databricks/databricks-gpt-6-1-terra": { + "cache_creation_input_token_cost": 1.24999e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.49998e-06, + "cache_read_input_token_cost": 4.998e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.0003e-07, + "input_cost_per_token": 1.00002e-06, + "input_cost_per_token_above_272k_tokens": 1.99997e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.00003e-06, + "output_cost_per_token_above_272k_tokens": 7.50001e-06, + "output_dbu_cost_per_token": 7.1429e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "input_cost_per_token_priority": 1.99997e-06, + "output_cost_per_token_priority": 9.99999e-06, + "cache_read_input_token_cost_priority": 1.0003e-07, + "cache_creation_input_token_cost_priority": 2.49998e-06, + "input_cost_per_token_above_272k_tokens_priority": 4.00001e-06, + "output_cost_per_token_above_272k_tokens_priority": 1.500002e-05, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.9999e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 5.00003e-06 + }, + "databricks/gpt-terra-latest": { + "alias_of": "databricks/databricks-gpt-6-1-terra" + }, + "databricks/databricks-gpt-6-astra": { + "cache_creation_input_token_cost": 1.249997e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1.00002e-06, + "cache_read_input_token_cost_above_272k_tokens": 1.99997e-06, + "input_cost_per_token": 9.99999e-06, + "input_cost_per_token_above_272k_tokens": 2e-05, + "input_dbu_cost_per_token": 0.00014286, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.000002e-05, + "output_cost_per_token_above_272k_tokens": 7.50001e-05, + "output_dbu_cost_per_token": 0.00071429, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "input_cost_per_token_priority": 1.999998e-05, + "output_cost_per_token_priority": 9.99999e-05, + "cache_read_input_token_cost_priority": 1.99997e-06, + "cache_creation_input_token_cost_priority": 2.500001e-05, + "input_cost_per_token_above_272k_tokens_priority": 4.000003e-05, + "output_cost_per_token_above_272k_tokens_priority": 0.0001500002, + "cache_read_input_token_cost_above_272k_tokens_priority": 4.00001e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 5.000002e-05 + }, + "databricks/gpt-astra-latest": { + "alias_of": "databricks/databricks-gpt-6-astra" + }, + "databricks/databricks-gpt-6-luna": { + "cache_creation_input_token_cost": 1.2502e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.4997e-07, + "cache_read_input_token_cost": 1.001e-08, + "cache_read_input_token_cost_above_272k_tokens": 2.002e-08, + "input_cost_per_token": 1.0003e-07, + "input_cost_per_token_above_272k_tokens": 1.9999e-07, + "input_dbu_cost_per_token": 1.429e-06, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 5.0001e-07, + "output_cost_per_token_above_272k_tokens": 7.497e-07, + "output_dbu_cost_per_token": 7.143e-06, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "input_cost_per_token_priority": 1.9999e-07, + "output_cost_per_token_priority": 1.0003e-06, + "cache_read_input_token_cost_priority": 2.002e-08, + "cache_creation_input_token_cost_priority": 2.4997e-07, + "input_cost_per_token_above_272k_tokens_priority": 3.9998e-07, + "output_cost_per_token_above_272k_tokens_priority": 1.5001e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 3.997e-08, + "cache_creation_input_token_cost_above_272k_tokens_priority": 5.0001e-07 + }, + "databricks/gpt-luna-latest": { + "alias_of": "databricks/databricks-gpt-6-luna" + }, + "databricks/databricks-gpt-6-sol": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.00003e-06, + "cache_read_input_token_cost": 1.9999e-07, + "cache_read_input_token_cost_above_272k_tokens": 3.9998e-07, + "input_cost_per_token": 1.99997e-06, + "input_cost_per_token_above_272k_tokens": 4.00001e-06, + "input_dbu_cost_per_token": 2.8571e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 9.99999e-06, + "output_cost_per_token_above_272k_tokens": 1.50003e-05, + "output_dbu_cost_per_token": 0.00014286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "input_cost_per_token_priority": 4.00001e-06, + "output_cost_per_token_priority": 1.99997e-05, + "cache_read_input_token_cost_priority": 3.9998e-07, + "cache_creation_input_token_cost_priority": 5.00003e-06, + "input_cost_per_token_above_272k_tokens_priority": 8.00002e-06, + "output_cost_per_token_above_272k_tokens_priority": 2.99999e-05, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.0003e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 9.99999e-06 + }, + "databricks/databricks-gpt-image-1": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 1.24999e-06, + "input_cost_per_image_token": 9.99999e-06, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "image_generation", + "output_cost_per_image_token": 4.000003e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" + }, + "databricks/databricks-gpt-image-1-5": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 1.24999e-06, + "input_cost_per_image_token": 8.00002e-06, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "image_generation", + "output_cost_per_image_token": 3.200001e-05, + "output_cost_per_token": 9.99999e-06, + "output_dbu_cost_per_token": 0.00014286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_pdf_input": true, + "supports_vision": true + }, + "databricks/databricks-gpt-image-1-mini": { + "cache_creation_input_token_cost": 1.99997e-06, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_image_token": 2.49998e-06, + "input_cost_per_token": 1.99997e-06, + "input_dbu_cost_per_token": 2.8571e-05, + "litellm_provider": "databricks", + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "image_generation", + "output_cost_per_image_token": 8.00002e-06, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" + }, + "databricks/databricks-gpt-image-2": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 1.24999e-06, + "input_cost_per_image_token": 8.00002e-06, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "image_generation", + "output_cost_per_image_token": 2.999997e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_pdf_input": true, + "supports_vision": true + }, + "databricks/databricks-grok-4-7": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 6.2503e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 7.50001e-06, + "output_dbu_cost_per_token": 0.00010714, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/grok-latest": { + "alias_of": "databricks/databricks-grok-4-7" + }, + "databricks/databricks-kimi-k2-7": { + "cache_creation_input_token_cost": 9.4997e-07, + "cache_read_input_token_cost": 1.8998e-07, + "deprecation_date": "2026-10-30", + "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/retired-models-policy", + "input_cost_per_token": 9.4997e-07, + "input_dbu_cost_per_token": 1.3571e-05, + "litellm_provider": "databricks", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 4.00001e-06, + "output_dbu_cost_per_token": 5.7143e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "successor_model": "databricks/databricks-kimi-k3", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/spot-deepseek-v4-flash": { + "cache_read_input_token_cost": 2.1e-08, + "deprecation_date": "2026-08-14", + "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", + "input_cost_per_token": 1.05e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.1e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "successor_model": "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/routers/kimi-k3-spot": { + "cache_read_input_token_cost": 2.1e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-spot": { + "cache_read_input_token_cost": 1.82e-07, + "input_cost_per_token": 9.8e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.08e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-spot": { + "cache_read_input_token_cost": 4.2e-09, + "input_cost_per_token": 2.1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 8.4e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast": { + "cache_read_input_token_cost": 4.8e-08, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 9.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing.md", + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot": { + "cache_read_input_token_cost": 4.2e-09, + "input_cost_per_token": 2.1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 8.4e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bigmodel/glm-5.3": { + "input_cost_per_token": 1.1428571428571428e-06, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 2.857142857142857e-07, + "litellm_provider": "bigmodel", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "source": "https://docs.bigmodel.cn/cn/guide/start/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "thinking_always_on": true, + "metadata": { + "comment": "Official API list price checked 2026-10-27: input 8, output 28, cached input 2 CNY per million tokens; converted at 7.0 CNY/USD. Cache storage is temporarily free and is not encoded." + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_native_streaming": true + }, + "bigmodel/glm-5.3-flash": { + "input_cost_per_token": 1.142857142857143e-07, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 3.2857142857142855e-08, + "litellm_provider": "bigmodel", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "source": "https://docs.bigmodel.cn/cn/guide/start/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "thinking_always_on": true, + "supports_vision": true, + "supports_video_input": true, + "metadata": { + "comment": "Official API list price checked 2026-10-27: input 0.8, output 2.8, cached input 0.23 CNY per million tokens; converted at 7.0 CNY/USD. Cache storage is temporarily free and is not encoded." + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_native_streaming": true + }, + "bigmodel/glm-5.3-flashx": { + "input_cost_per_token": 2.857142857142857e-07, + "output_cost_per_token": 1e-06, + "cache_read_input_token_cost": 8.142857142857142e-08, + "litellm_provider": "bigmodel", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "source": "https://docs.bigmodel.cn/cn/guide/start/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "thinking_always_on": true, + "supports_vision": true, + "supports_video_input": true, + "metadata": { + "comment": "Official API list price checked 2026-10-27: input 2, output 7, cached input 0.57 CNY per million tokens; converted at 7.0 CNY/USD. Cache storage is temporarily free and is not encoded." + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_native_streaming": true + }, + "fireworks_ai/accounts/fireworks/models/ultramarine-1-flash-us": { + "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_priority": 3.75e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_priority": 1.875e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_priority": 6.25e-07, + "source": "https://docs.fireworks.ai/serverless/pricing.md", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "baseten/decision-models/baseten-joey-2b-latest": { + "input_cost_per_token": 1e-08, + "litellm_provider": "baseten", + "max_input_tokens": 16384, + "mode": "decisions", + "output_cost_per_token": 0.0, + "source": "https://inference.baseten.co/v1/models", + "supports_vision": true + }, + "gpt-6-rosalind": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_12hr": 3.75e-05, + "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 7.5e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3.75e-05, + "cache_read_input_token_cost": 1.5e-06, + "cache_read_input_token_cost_above_272k_tokens": 3e-06, + "input_cost_per_token": 1.5e-05, + "input_cost_per_token_above_272k_tokens": 3e-05, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_above_272k_tokens": 0.0001125, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6-rosalind": { + "litellm_provider": "chatgpt", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "gpt-6-cyber": { + "cache_creation_input_token_cost": 2.5e-05, + "cache_creation_input_token_cost_above_12hr": 5e-05, + "cache_read_input_token_cost": 2e-06, + "cache_read_input_token_cost_above_272k_tokens": 4e-06, + "input_cost_per_token": 2e-05, + "input_cost_per_token_above_272k_tokens": 4e-05, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0001, + "output_cost_per_token_above_272k_tokens": 0.00015, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true + }, + "gpt-6-astra-law": { + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "reasoning_contexts": [ + "auto", + "current_turn", + "all_turns" + ], + "reasoning_modes": [ + "standard", + "pro" + ], + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "fedramp_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6-astra-law": { + "litellm_provider": "chatgpt", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "nebius/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "max_input_tokens": 1048576, + "input_cost_per_token": 3e-07, + "cache_read_input_token_cost": 6e-09, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_vision": true, + "supports_reasoning": true, + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info" + }, + "nebius/meta-models/muse-spark-open": { + "max_input_tokens": 1048576, + "input_cost_per_token": 1.25e-06, + "cache_read_input_token_cost": 1.5e-07, + "output_cost_per_token": 4.25e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_vision": true, + "supports_video_input": true, + "supports_reasoning": true, + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info" + }, + "nebius/MiniMaxAI/MiniMax-M3.1-Flash": { + "max_input_tokens": 1048576, + "input_cost_per_token": 1.5e-07, + "cache_read_input_token_cost": 1.5e-08, + "output_cost_per_token": 6e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_vision": true, + "supports_reasoning": true, + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info" + }, + "nebius/nvidia/Nemotron-3.5-Super-VL": { + "max_input_tokens": 1048576, + "input_cost_per_token": 3e-07, + "cache_read_input_token_cost": 6e-08, + "output_cost_per_token": 9e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_vision": true, + "supports_video_input": true, + "supports_reasoning": true, + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/api/public/models_info" + }, + "empiriolabs/aplomb-1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 0.0, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages", + "/v1/decisions" + ], + "supports_vision": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/aplomb-1" + }, + "empiriolabs/deepseek-v4-1-flash-1017": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 8e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/deepseek-v4-1-flash-1017", + "cache_read_input_token_cost": 2e-08, + "supports_prompt_caching": true, + "supports_function_calling": true + }, + "empiriolabs/deepseek-v4-flash-0731": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 4.24e-07, + "output_cost_per_token": 1.272e-06, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/deepseek-v4-flash-0731", + "supports_function_calling": true + }, + "empiriolabs/deepseek-v4-flash-0731:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 4.4e-07, + "output_cost_per_token": 1.32e-06, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/deepseek-v4-flash-0731", + "supports_function_calling": true + }, + "empiriolabs/deepseek-v4-pro": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 1.65e-06, + "output_cost_per_token": 3.3e-06, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/deepseek-v4-pro", + "supports_function_calling": true + }, + "empiriolabs/deepseek-v4-pro-0813": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 1.32e-06, + "output_cost_per_token": 3.96e-06, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/deepseek-v4-pro-0813", + "supports_function_calling": true + }, + "empiriolabs/deepseek-v4-pro:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 4.8e-06, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02, + "search_context_size_high": 0.02 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/deepseek-v4-pro", + "supports_function_calling": true + }, + "empiriolabs/deepseek-v4-pro:variant2": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 1.65e-06, + "output_cost_per_token": 3.301e-06, + "cache_read_input_token_cost": 1.38e-07, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/deepseek-v4-pro", + "supports_function_calling": true + }, + "empiriolabs/deepseek-v4-pro:variant3": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 4.8e-06, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/deepseek-v4-pro", + "supports_function_calling": true + }, + "empiriolabs/fugu-max": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.5e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.007, + "search_context_size_medium": 0.007, + "search_context_size_high": 0.007 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/fugu-max" + }, + "empiriolabs/fugu-ultra-v1-0": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 7.5e-06, + "output_cost_per_token": 4.5e-05, + "input_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 6.75e-05, + "cache_read_input_token_cost_above_272k_tokens": 3e-06, + "cache_read_input_token_cost": 1.5e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/fugu-ultra-v1-0" + }, + "empiriolabs/fugu-ultra-v1-1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 3e-05, + "input_cost_per_token_above_272k_tokens": 1e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost": 5e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/fugu-ultra-v1-1" + }, + "empiriolabs/fugu-ultra-v2-0": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 3e-05, + "input_cost_per_token_above_272k_tokens": 1e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost": 5e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/fugu-ultra-v2-0" + }, + "empiriolabs/gemma-4-26b-a4b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2.9e-07, + "cache_read_input_token_cost": 2.5e-08, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/gemma-4-26b-a4b" + }, + "empiriolabs/glm-4-6v-flashx": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "input_cost_per_token": 4e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 3.6e-08, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.033, + "search_context_size_medium": 0.033, + "search_context_size_high": 0.033 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/glm-4-6v-flashx" + }, + "empiriolabs/glm-4-7-flashx": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 202752, + "max_output_tokens": 131072, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 6.3e-08, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.033, + "search_context_size_medium": 0.033, + "search_context_size_high": 0.033 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/glm-4-7-flashx" + }, + "empiriolabs/glm-5-1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 202745, + "max_output_tokens": 128000, + "input_cost_per_token": 8.25e-07, + "output_cost_per_token": 3.301e-06, + "input_cost_per_token_above_32k_tokens": 1.1e-06, + "output_cost_per_token_above_32k_tokens": 3.851e-06, + "cache_read_input_token_cost_above_32k_tokens": 2.2e-07, + "cache_read_input_token_cost": 1.65e-07, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/glm-5-1" + }, + "empiriolabs/glm-5-2": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.033, + "search_context_size_medium": 0.033, + "search_context_size_high": 0.033 + }, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/glm-5-2" + }, + "empiriolabs/glm-5-2:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.1e-06, + "output_cost_per_token": 3.851e-06, + "cache_read_input_token_cost": 2.75e-07, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.013, + "search_context_size_medium": 0.013, + "search_context_size_high": 0.013 + }, + "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/glm-5-2", + "supports_function_calling": true + }, + "empiriolabs/glm-5-2:variant2": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.013, + "search_context_size_medium": 0.013, + "search_context_size_high": 0.013 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/glm-5-2", + "supports_function_calling": true + }, + "empiriolabs/glm-5-3": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.033, + "search_context_size_medium": 0.033, + "search_context_size_high": 0.033 + }, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/glm-5-3" + }, + "empiriolabs/glm-5-3-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 2.5e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.033, + "search_context_size_medium": 0.033, + "search_context_size_high": 0.033 + }, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/glm-5-3-flash" + }, + "empiriolabs/kimi-k2-6": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 16000, + "input_cost_per_token": 8.939e-07, + "output_cost_per_token": 3.7131e-06, + "cache_read_input_token_cost": 1.788e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/kimi-k2-6", + "supports_function_calling": true + }, + "empiriolabs/kimi-k2-7-code": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/kimi-k2-7-code", + "supports_function_calling": true + }, + "empiriolabs/kimi-k2-7-code-highspeed": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 1.9e-06, + "output_cost_per_token": 8e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/kimi-k2-7-code-highspeed", + "supports_function_calling": true + }, + "empiriolabs/kimi-k2-7-code:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "input_cost_per_token": 8.939e-07, + "output_cost_per_token": 3.7131e-06, + "cache_read_input_token_cost": 1.788e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.013, + "search_context_size_medium": 0.013, + "search_context_size_high": 0.013 + }, + "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/kimi-k2-7-code", + "supports_function_calling": true + }, + "empiriolabs/kimi-k3": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/kimi-k3", + "supports_function_calling": true + }, + "empiriolabs/kimi-k3-1-pro": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.8e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/kimi-k3-1-pro" + }, + "empiriolabs/mimo-v2-6-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/mimo-v2-6-flash", + "supports_function_calling": true + }, + "empiriolabs/mimo-v2-6-pro": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 4.35e-07, + "output_cost_per_token": 8.7e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/mimo-v2-6-pro", + "supports_function_calling": true + }, + "empiriolabs/mimo-v2-6-pro-ultraspeed": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 4.35e-06, + "output_cost_per_token": 8.7e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/mimo-v2-6-pro-ultraspeed", + "supports_function_calling": true + }, + "empiriolabs/minimax-m2-7": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 3e-08, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/minimax-m2-7" + }, + "empiriolabs/minimax-m2-7-highspeed": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 3e-08, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/minimax-m2-7-highspeed" + }, + "empiriolabs/minimax-m3": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 524288, + "input_cost_per_token": 2.25e-07, + "output_cost_per_token": 9e-07, + "input_cost_per_token_above_512k_tokens": 4.5e-07, + "output_cost_per_token_above_512k_tokens": 1.8e-06, + "cache_read_input_token_cost_above_512k_tokens": 9e-08, + "cache_read_input_token_cost": 4.5e-08, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/minimax-m3" + }, + "empiriolabs/minimax-m3-1-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 524288, + "input_cost_per_token": 1.125e-07, + "output_cost_per_token": 4.5e-07, + "cache_read_input_token_cost": 1.125e-08, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/minimax-m3-1-flash" + }, + "empiriolabs/minimax-m3:priority": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048458, + "max_output_tokens": 524288, + "input_cost_per_token": 3.375e-07, + "output_cost_per_token": 1.35e-06, + "input_cost_per_token_above_512k_tokens": 6.75e-07, + "output_cost_per_token_above_512k_tokens": 2.7e-06, + "cache_read_input_token_cost_above_512k_tokens": 1.35e-07, + "cache_read_input_token_cost": 6.75e-08, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/minimax-m3" + }, + "empiriolabs/mistral-small-4": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.084, + "search_context_size_medium": 0.084, + "search_context_size_high": 0.14 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/mistral-small-4", + "supports_function_calling": true + }, + "empiriolabs/muse-glimmer-30b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 8e-07, + "cache_read_input_token_cost": 5e-08, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/muse-glimmer-30b", + "supports_function_calling": true + }, + "empiriolabs/muse-spark-1-1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 4.25e-06, + "cache_read_input_token_cost": 1e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/muse-spark-1-1" + }, + "empiriolabs/muse-spark-1-2": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 4.25e-06, + "cache_read_input_token_cost": 1e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/muse-spark-1-2" + }, + "empiriolabs/muse-spark-1-3": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 4.25e-06, + "cache_read_input_token_cost": 1e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/muse-spark-1-3" + }, + "empiriolabs/nova-lite-1-0": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 317379, + "max_output_tokens": 10000, + "input_cost_per_token": 6.9e-08, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 3.86e-08, + "supports_system_messages": true, + "supports_vision": true, + "supports_prompt_caching": true, + "source": "https://empiriolabs.ai/models/nova-lite-1-0", + "supports_function_calling": true + }, + "empiriolabs/nova-lite-2": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 3.16e-06, + "cache_read_input_token_cost": 2.128e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "source": "https://empiriolabs.ai/models/nova-lite-2", + "supports_function_calling": true + }, + "empiriolabs/nova-micro-1-0": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 133003, + "max_output_tokens": 10000, + "input_cost_per_token": 4e-08, + "output_cost_per_token": 1.6e-07, + "cache_read_input_token_cost": 2.24e-08, + "supports_system_messages": true, + "supports_prompt_caching": true, + "source": "https://empiriolabs.ai/models/nova-micro-1-0", + "supports_function_calling": true + }, + "empiriolabs/nova-pro-1-0": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 317319, + "max_output_tokens": 10000, + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 9.6e-06, + "supports_system_messages": true, + "supports_vision": true, + "source": "https://empiriolabs.ai/models/nova-pro-1-0", + "supports_function_calling": true + }, + "empiriolabs/perplexity-advanced-deep-research": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_output_tokens": 16000, + "input_cost_per_token": 1.2e-05, + "output_cost_per_token": 6e-05, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.012, + "search_context_size_medium": 0.012, + "search_context_size_high": 0.012 + }, + "source": "https://empiriolabs.ai/models/perplexity-advanced-deep-research" + }, + "empiriolabs/perplexity-deep-research": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 919327, + "input_cost_per_token": 4.8e-06, + "output_cost_per_token": 1.9e-05, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "source": "https://empiriolabs.ai/models/perplexity-deep-research" + }, + "empiriolabs/perplexity-pro-search": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_output_tokens": 32768, + "input_cost_per_token": 7.8e-06, + "output_cost_per_token": 3.9e-05, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "source": "https://empiriolabs.ai/models/perplexity-pro-search" + }, + "empiriolabs/perplexity-sonar": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 919327, + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 2.4e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "source": "https://empiriolabs.ai/models/perplexity-sonar" + }, + "empiriolabs/perplexity-sonar-pro": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 919328, + "max_output_tokens": 32768, + "input_cost_per_token": 7.2e-06, + "output_cost_per_token": 3.6e-05, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "source": "https://empiriolabs.ai/models/perplexity-sonar-pro" + }, + "empiriolabs/perplexity-sonar-reasoning-pro": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 919330, + "max_output_tokens": 131072, + "input_cost_per_token": 4.8e-06, + "output_cost_per_token": 1.9e-05, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "source": "https://empiriolabs.ai/models/perplexity-sonar-reasoning-pro" + }, + "empiriolabs/qwen3-5-122b-a10b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 258048, + "max_output_tokens": 64000, + "input_cost_per_token": 1.15e-07, + "output_cost_per_token": 9.17e-07, + "input_cost_per_token_above_128k_tokens": 2.87e-07, + "output_cost_per_token_above_128k_tokens": 2.294e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-122b-a10b", + "supports_function_calling": true + }, + "empiriolabs/qwen3-5-27b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 258048, + "max_output_tokens": 64000, + "input_cost_per_token": 8.6e-08, + "output_cost_per_token": 6.88e-07, + "input_cost_per_token_above_128k_tokens": 2.58e-07, + "output_cost_per_token_above_128k_tokens": 2.064e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-27b", + "supports_function_calling": true + }, + "empiriolabs/qwen3-5-35b-a3b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 258048, + "max_output_tokens": 64000, + "input_cost_per_token": 5.7e-08, + "output_cost_per_token": 4.59e-07, + "input_cost_per_token_above_128k_tokens": 2.29e-07, + "output_cost_per_token_above_128k_tokens": 1.835e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-35b-a3b", + "supports_function_calling": true + }, + "empiriolabs/qwen3-5-397b-a17b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 258048, + "max_output_tokens": 64000, + "input_cost_per_token": 1.72e-07, + "output_cost_per_token": 1.032e-06, + "input_cost_per_token_above_128k_tokens": 4.3e-07, + "output_cost_per_token_above_128k_tokens": 2.58e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-397b-a17b", + "supports_function_calling": true + }, + "empiriolabs/qwen3-5-4b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "input_cost_per_token": 4e-08, + "output_cost_per_token": 7e-08, + "cache_read_input_token_cost": 2e-08, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-4b" + }, + "empiriolabs/qwen3-5-9b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.3e-07, + "cache_read_input_token_cost": 4.5e-08, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-9b" + }, + "empiriolabs/qwen3-5-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 995904, + "max_output_tokens": 32768, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3.68e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-flash", + "supports_function_calling": true + }, + "empiriolabs/qwen3-5-flash:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 995904, + "max_output_tokens": 65536, + "input_cost_per_token": 2.9e-08, + "output_cost_per_token": 2.87e-07, + "input_cost_per_token_above_128k_tokens": 1.15e-07, + "output_cost_per_token_above_128k_tokens": 1.147e-06, + "input_cost_per_token_above_256k_tokens": 1.72e-07, + "output_cost_per_token_above_256k_tokens": 1.72e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-flash", + "supports_function_calling": true + }, + "empiriolabs/qwen3-5-omni-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 196608, + "max_output_tokens": 32768, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 4.4e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/qwen3-5-omni-flash", + "supports_function_calling": true + }, + "empiriolabs/qwen3-5-omni-plus": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 196608, + "max_output_tokens": 32768, + "input_cost_per_token": 2.8e-06, + "output_cost_per_token": 1.66e-05, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/qwen3-5-omni-plus", + "supports_function_calling": true + }, + "empiriolabs/qwen3-5-plus": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 3.6e-07, + "output_cost_per_token": 2.21e-06, + "input_cost_per_token_above_256k_tokens": 4.5e-07, + "output_cost_per_token_above_256k_tokens": 2.76e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.015, + "search_context_size_medium": 0.015, + "search_context_size_high": 0.015 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-plus", + "supports_function_calling": true + }, + "empiriolabs/qwen3-5-plus:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 1.15e-07, + "output_cost_per_token": 6.88e-07, + "input_cost_per_token_above_128k_tokens": 2.87e-07, + "output_cost_per_token_above_128k_tokens": 1.72e-06, + "input_cost_per_token_above_256k_tokens": 5.73e-07, + "output_cost_per_token_above_256k_tokens": 3.44e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-5-plus", + "supports_function_calling": true + }, + "empiriolabs/qwen3-6-27b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 229376, + "max_output_tokens": 64000, + "input_cost_per_token": 4.12564e-07, + "output_cost_per_token": 2.475384e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-6-27b", + "supports_function_calling": true + }, + "empiriolabs/qwen3-6-35b-a3b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 4.2e-07, + "cache_read_input_token_cost": 3.5e-08, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-6-35b-a3b", + "supports_function_calling": true + }, + "empiriolabs/qwen3-6-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.5e-06, + "input_cost_per_token_above_256k_tokens": 1e-06, + "output_cost_per_token_above_256k_tokens": 4e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02, + "search_context_size_high": 0.02 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-6-flash", + "supports_function_calling": true + }, + "empiriolabs/qwen3-6-flash:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 1.65e-07, + "output_cost_per_token": 9.9e-07, + "input_cost_per_token_above_256k_tokens": 6.6e-07, + "output_cost_per_token_above_256k_tokens": 3.961e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-6-flash", + "supports_function_calling": true + }, + "empiriolabs/qwen3-6-plus": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "input_cost_per_token_above_256k_tokens": 2e-06, + "output_cost_per_token_above_256k_tokens": 6e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.026, + "search_context_size_medium": 0.026, + "search_context_size_high": 0.026 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-6-plus", + "supports_function_calling": true + }, + "empiriolabs/qwen3-6-plus:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 2.76e-07, + "output_cost_per_token": 1.651e-06, + "input_cost_per_token_above_256k_tokens": 1.101e-06, + "output_cost_per_token_above_256k_tokens": 6.602e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-6-plus", + "supports_function_calling": true + }, + "empiriolabs/qwen3-7-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 1.3e-07, + "input_cost_per_token_above_32k_tokens": 1e-07, + "output_cost_per_token_above_32k_tokens": 4e-07, + "cache_read_input_token_cost_above_32k_tokens": 2e-08, + "input_cost_per_token_above_256k_tokens": 2e-07, + "output_cost_per_token_above_256k_tokens": 8e-07, + "cache_read_input_token_cost_above_256k_tokens": 4e-08, + "cache_read_input_token_cost": 6e-09, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.03, + "search_context_size_medium": 0.03, + "search_context_size_high": 0.03 + }, + "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-7-flash", + "supports_function_calling": true + }, + "empiriolabs/qwen3-7-flash:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 2.8e-08, + "output_cost_per_token": 1.1e-07, + "input_cost_per_token_above_32k_tokens": 8.3e-08, + "output_cost_per_token_above_32k_tokens": 3.3e-07, + "cache_read_input_token_cost_above_32k_tokens": 1.7e-08, + "input_cost_per_token_above_256k_tokens": 1.65e-07, + "output_cost_per_token_above_256k_tokens": 6.6e-07, + "cache_read_input_token_cost_above_256k_tokens": 3.3e-08, + "cache_read_input_token_cost": 6e-09, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-7-flash", + "supports_function_calling": true + }, + "empiriolabs/qwen3-7-max": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 7.5e-06, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02, + "search_context_size_high": 0.02 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-7-max", + "supports_function_calling": true + }, + "empiriolabs/qwen3-7-max:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 1.65e-06, + "output_cost_per_token": 4.951e-06, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-7-max", + "supports_function_calling": true + }, + "empiriolabs/qwen3-7-plus": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 1.6e-06, + "input_cost_per_token_above_256k_tokens": 1.2e-06, + "output_cost_per_token_above_256k_tokens": 4.8e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.03, + "search_context_size_medium": 0.03, + "search_context_size_high": 0.03 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-7-plus", + "supports_function_calling": true + }, + "empiriolabs/qwen3-7-plus:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 65536, + "input_cost_per_token": 2.76e-07, + "output_cost_per_token": 1.101e-06, + "input_cost_per_token_above_256k_tokens": 8.26e-07, + "output_cost_per_token_above_256k_tokens": 3.301e-06, + "cache_read_input_token_cost_above_256k_tokens": 1.66e-07, + "cache_read_input_token_cost": 5.6e-08, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_prompt_caching": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-7-plus", + "supports_function_calling": true + }, + "empiriolabs/qwen3-8-27b": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "input_cost_per_token": 1.7e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 8e-08, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-8-27b" + }, + "empiriolabs/qwen3-8-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 131072, + "input_cost_per_token": 1.6e-07, + "output_cost_per_token": 4.7e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02, + "search_context_size_high": 0.02 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-8-flash", + "supports_function_calling": true + }, + "empiriolabs/qwen3-8-max": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02, + "search_context_size_high": 0.02 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-8-max", + "supports_function_calling": true + }, + "empiriolabs/qwen3-8-max-0902": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02, + "search_context_size_high": 0.02 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-8-max-0902", + "supports_function_calling": true + }, + "empiriolabs/qwen3-8-max:variant1": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 983616, + "max_output_tokens": 131072, + "input_cost_per_token": 1.65e-06, + "output_cost_per_token": 4.951e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01, + "search_context_size_high": 0.01 + }, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/qwen3-8-max", + "supports_function_calling": true + }, + "empiriolabs/qwen3-8-omni-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1006592, + "max_output_tokens": 131072, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 9.4e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.02, + "search_context_size_medium": 0.02, + "search_context_size_high": 0.02 + }, + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/qwen3-8-omni-flash", + "supports_function_calling": true + }, + "empiriolabs/seed-2-0-code": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 229096, + "max_output_tokens": 128000, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2.4e-06, + "input_cost_per_token_above_128k_tokens": 8e-07, + "output_cost_per_token_above_128k_tokens": 4.8e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "source": "https://empiriolabs.ai/models/seed-2-0-code", + "supports_function_calling": true + }, + "empiriolabs/seed-2-0-lite": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 229096, + "max_output_tokens": 128000, + "input_cost_per_token": 3.1e-07, + "output_cost_per_token": 2.5e-06, + "input_cost_per_token_above_128k_tokens": 6.2e-07, + "output_cost_per_token_above_128k_tokens": 5e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/seed-2-0-lite", + "supports_function_calling": true + }, + "empiriolabs/seed-2-0-mini": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 229156, + "max_output_tokens": 128000, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 5e-07, + "input_cost_per_token_above_128k_tokens": 2.4e-07, + "output_cost_per_token_above_128k_tokens": 1e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/seed-2-0-mini", + "supports_function_calling": true + }, + "empiriolabs/seed-2-0-pro": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 229096, + "max_output_tokens": 128000, + "input_cost_per_token": 6.3e-07, + "output_cost_per_token": 3.79e-06, + "input_cost_per_token_above_128k_tokens": 1.26e-06, + "output_cost_per_token_above_128k_tokens": 7.58e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/seed-2-0-pro", + "supports_function_calling": true + }, + "empiriolabs/seed-2-1-turbo": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 229093, + "max_output_tokens": 65536, + "input_cost_per_token": 6.3e-07, + "output_cost_per_token": 3.13e-06, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/seed-2-1-turbo", + "supports_function_calling": true + }, + "empiriolabs/skylark-embedding-vision": { + "litellm_provider": "empiriolabs", + "mode": "embedding", + "max_input_tokens": 8000, + "input_cost_per_token": 2.5e-07, + "supports_embedding_image_input": true, + "source": "https://empiriolabs.ai/models/skylark-embedding-vision" + }, + "empiriolabs/step-3-5-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 2e-08, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.013, + "search_context_size_medium": 0.013, + "search_context_size_high": 0.013 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/step-3-5-flash" + }, + "empiriolabs/step-3-5-flash-2603": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 2e-08, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.013, + "search_context_size_medium": 0.013, + "search_context_size_high": 0.013 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "source": "https://empiriolabs.ai/models/step-3-5-flash-2603" + }, + "empiriolabs/step-3-7-flash": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.15e-06, + "cache_read_input_token_cost": 4e-08, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.013, + "search_context_size_medium": 0.013, + "search_context_size_high": 0.013 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/step-3-7-flash" + }, + "empiriolabs/step-5-preview": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 1024000, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 1e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "source": "https://empiriolabs.ai/models/step-5-preview" + }, + "empiriolabs/stepaudio-2-5-chat": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 3.5e-06, + "cache_read_input_token_cost": 3e-07, + "supports_system_messages": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.013, + "search_context_size_medium": 0.013, + "search_context_size_high": 0.013 + }, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/stepaudio-2-5-chat" + }, + "empiriolabs/stepaudio-3-chat": { + "litellm_provider": "empiriolabs", + "mode": "chat", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 3.5e-06, + "cache_read_input_token_cost": 3e-07, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_prompt_caching": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_audio_input": true, + "source": "https://empiriolabs.ai/models/stepaudio-3-chat" + }, + "empiriolabs/text-embedding-v4": { + "litellm_provider": "empiriolabs", + "mode": "embedding", + "max_input_tokens": 8192, + "input_cost_per_token": 7e-08, + "source": "https://empiriolabs.ai/models/text-embedding-v4" + }, + "empiriolabs/tongyi-embedding-vision-flash": { + "litellm_provider": "empiriolabs", + "mode": "embedding", + "max_input_tokens": 1024, + "input_cost_per_token": 9e-08, + "supports_embedding_image_input": true, + "source": "https://empiriolabs.ai/models/tongyi-embedding-vision-flash" + }, + "empiriolabs/tongyi-embedding-vision-plus": { + "litellm_provider": "empiriolabs", + "mode": "embedding", + "max_input_tokens": 1024, + "input_cost_per_token": 9e-08, + "supports_embedding_image_input": true, + "source": "https://empiriolabs.ai/models/tongyi-embedding-vision-plus" + }, + "wally/glm-5.3-flash": { + "cache_read_input_token_cost": 7.6e-08, + "input_cost_per_token": 2.72e-07, + "litellm_provider": "wally", + "max_input_tokens": 1048567, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6.5e-07, + "reasoning_effort_levels": [ + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "wally/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "wally", + "max_input_tokens": 1048569, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "wally/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "wally", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "wally/deepseek-v4.1-flash-fast": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "wally", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "wally/glm-5.3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "wally", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "wally/deepseek-v4-pro-fast": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 1.91e-06, + "litellm_provider": "wally", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.83e-06, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "wally/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "wally", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "wally/minimax-m3": { + "cache_read_input_token_cost": 6.6e-08, + "input_cost_per_token": 3.3e-07, + "litellm_provider": "wally", + "max_input_tokens": 524287, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://www.runwally.com/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "wally/deepseek-v4.1-flash-1017": { + "cache_read_input_token_cost": 8e-09, + "input_cost_per_token": 3.75e-07, + "litellm_provider": "wally", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "max" + ], + "source": "https://inference.runanywhere.ai/v1/models", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "wally/deepseek-v4.1-flash-f2": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "wally", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "max" + ], + "source": "https://inference.runanywhere.ai/v1/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "together_ai/moonshotai/Kimi-K3.1-Pro": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3.6e-06, + "input_cost_per_token_batches": 1.8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "output_cost_per_token_batches": 9e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-east-1/index.json", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 4.5e-06, + "cache_read_input_token_cost": 3.6e-07, + "input_cost_per_token": 3.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-east-1/index.json", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3.6e-06, + "input_cost_per_token_batches": 1.8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "output_cost_per_token_batches": 9e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 4.5e-06, + "cache_read_input_token_cost": 3.6e-07, + "input_cost_per_token": 3.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-east-1/nvidia.nemotron-nano-12b-v2": { + "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "input_cost_per_token_flex": 1.2e-07, + "input_cost_per_token_priority": 4.2e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-east-1/nvidia.nemotron-nano-3-30b": { + "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 262144, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.88e-07, + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 5.04e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "bedrock_mantle/us-gov-east-1/nvidia.nemotron-nano-9b-v2": { + "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.76e-07, + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 4.8e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": false + }, + "bedrock_mantle/us-gov-east-1/nvidia.nemotron-super-3-120b": { + "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.8e-07, + "output_cost_per_token_batches": 3.9e-07, + "output_cost_per_token_flex": 3.9e-07, + "output_cost_per_token_priority": 1.365e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "bedrock_mantle/us-gov-west-1/nvidia.nemotron-nano-12b-v2": { + "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "input_cost_per_token_flex": 1.2e-07, + "input_cost_per_token_priority": 4.2e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "output_cost_per_token_flex": 3.6e-07, + "output_cost_per_token_priority": 1.26e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-west-1/nvidia.nemotron-nano-3-30b": { + "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 262144, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.88e-07, + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 5.04e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "bedrock_mantle/us-gov-west-1/nvidia.nemotron-nano-9b-v2": { + "input_cost_per_token": 7.2e-08, + "input_cost_per_token_batches": 3.6e-08, + "input_cost_per_token_flex": 3.6e-08, + "input_cost_per_token_priority": 1.32e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.76e-07, + "output_cost_per_token_batches": 1.44e-07, + "output_cost_per_token_flex": 1.44e-07, + "output_cost_per_token_priority": 4.8e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": false + }, + "bedrock_mantle/us-gov-west-1/nvidia.nemotron-super-3-120b": { + "input_cost_per_token": 1.8e-07, + "input_cost_per_token_batches": 9e-08, + "input_cost_per_token_flex": 9e-08, + "input_cost_per_token_priority": 3.15e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.8e-07, + "output_cost_per_token_batches": 3.9e-07, + "output_cost_per_token_flex": 3.9e-07, + "output_cost_per_token_priority": 1.365e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "gmi/MiniMaxAI/MiniMax-M2": { + "input_cost_per_token": 3e-07, + "litellm_provider": "gmi", + "max_input_tokens": 196608, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/MiniMaxAI/MiniMax-M2.5": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "gmi", + "max_input_tokens": 196608, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/MiniMaxAI/MiniMax-M2.7": { + "cache_read_input_token_cost": 4.2e-08, + "input_cost_per_token": 2.1e-07, + "litellm_provider": "gmi", + "max_input_tokens": 196608, + "mode": "chat", + "output_cost_per_token": 8.4e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/MiniMaxAI/MiniMax-M3": { + "cache_read_input_token_cost": 4.8e-08, + "input_cost_per_token": 2.4e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 9.6e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/MiniMaxAI/MiniMax-M3.1-Flash": { + "cache_read_input_token_cost": 1.125e-08, + "input_cost_per_token": 1.125e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-235B-A22B-FP8": { + "input_cost_per_token": 1.7e-07, + "litellm_provider": "gmi", + "max_input_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.09e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8": { + "cache_read_input_token_cost": 1.75e-08, + "input_cost_per_token": 8.75e-08, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-235B-A22B-Thinking-2507-FP8": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262141, + "mode": "chat", + "output_cost_per_token": 4.2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-30B-A3B": { + "input_cost_per_token": 8e-08, + "litellm_provider": "gmi", + "max_input_tokens": 40946, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-32B-FP8": { + "input_cost_per_token": 1e-07, + "litellm_provider": "gmi", + "max_input_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 9e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262128, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-Next-80B-A3B-Instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3-Next-80B-A3B-Thinking": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.5-122B-A10B": { + "input_cost_per_token": 4e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.5-27B": { + "input_cost_per_token": 3e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.5-35B-A3B": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.5-397B-A17B": { + "input_cost_per_token": 6e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.6-35B-A3B": { + "input_cost_per_token": 2.48e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.485e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.6-Plus": { + "input_cost_per_token": 5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.6-Plus-2026-04-02": { + "input_cost_per_token": 5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.7-Max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.8-27B": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 4.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.8-Flash": { + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.6e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.8-Max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/Qwen/Qwen3.8-Max-0902": { + "cache_read_input_token_cost": 2.06e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.951e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/XiaomiMiMo/MiMo-V2.5": { + "cache_read_input_token_cost": 2.38e-09, + "input_cost_per_token": 1.19e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 2.38e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/XiaomiMiMo/MiMo-V2.5-Pro": { + "cache_read_input_token_cost": 2.52e-09, + "input_cost_per_token": 3.045e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 6.09e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/XiaomiMiMo/MiMo-V2.6-Flash": { + "cache_read_input_token_cost": 2.24e-09, + "input_cost_per_token": 1.12e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 2.24e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/XiaomiMiMo/MiMo-V2.6-Pro": { + "cache_read_input_token_cost": 2.88e-09, + "input_cost_per_token": 3.48e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 6.96e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-Prover-V2-671B": { + "input_cost_per_token": 5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.18e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.18e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-R1-0528": { + "cache_read_input_token_cost": 2.3e-07, + "input_cost_per_token": 5.7e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.29e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.9e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "input_cost_per_token": 2e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { + "input_cost_per_token": 5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { + "input_cost_per_token": 1e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V3.1": { + "input_cost_per_token": 2.7e-07, + "litellm_provider": "gmi", + "max_input_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V3.1-Terminus": { + "input_cost_per_token": 2.7e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V3.2-Exp": { + "input_cost_per_token": 2.7e-07, + "litellm_provider": "gmi", + "max_input_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 4.1e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V3.2-Speciale": { + "input_cost_per_token": 2.8e-07, + "litellm_provider": "gmi", + "max_input_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V4-Flash": { + "cache_read_input_token_cost": 1.82e-08, + "input_cost_per_token": 9.1e-08, + "litellm_provider": "gmi", + "max_input_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 1.82e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V4-Flash-0731": { + "cache_read_input_token_cost": 9.1e-09, + "input_cost_per_token": 2.86e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 8.58e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 3.52e-08, + "input_cost_per_token": 1.056e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 3.168e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 1.8e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/deepseek-v4-flash-vision-exp": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/deepseek-ai/deepseek-v4.1-flash-1017": { + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 1.8e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/gmicloud/Ripple-65B-Preview": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-3.1-pro-preview": { + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-3.5-flash": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 9e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-3.5-flash-lite": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-3.6-flash": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-3.7-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-3.8-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-4-argon": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemini-4-carbon": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemma-4-26b-a4b-it": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "gmi", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/google/gemma-4-31b-it": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 8e-08, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/moonshotai/Kimi-K2-Instruct-0905": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 5.7e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.29e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/moonshotai/Kimi-K2.5": { + "input_cost_per_token": 6e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/moonshotai/Kimi-K2.6": { + "cache_read_input_token_cost": 1.44e-07, + "input_cost_per_token": 8.55e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/moonshotai/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/moonshotai/kimi-k2.7-code-highspeed": { + "cache_read_input_token_cost": 3.8e-07, + "input_cost_per_token": 1.9e-06, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/moonshotai/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/moonshotai/kimi-k3.1-pro": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "gmi", + "max_input_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/nvidia/nemotron-3-ultra-550b-a55b": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 8e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.6e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.4": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.4-mini": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.4-nano": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.4-pro": { + "input_cost_per_token": 3e-05, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "mode": "chat", + "output_cost_per_token": 0.00018, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.5": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.6-luna": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.6-sol": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-5.6-terra": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-6-astra": { + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-6-luna": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-6-sol": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-6.1-sol": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1050000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-oss-120b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/openai/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/stepfun-ai/Step-3.7-Flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "gmi", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/stepfun-ai/Step-5-Preview": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.7e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/tencent/HunyuanOCR": { + "input_cost_per_token": 5e-07, + "litellm_provider": "gmi", + "max_input_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/tencent/Hy3": { + "cache_read_input_token_cost": 3.5e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 5.8e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/tencent/hy3-preview": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 1.8e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/tencent/hy4": { + "cache_read_input_token_cost": 2.1e-08, + "input_cost_per_token": 4.17e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.2505e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/tencent/hy4-preview": { + "cache_read_input_token_cost": 4.2e-08, + "input_cost_per_token": 8.34e-07, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.501e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/x-ai/grok-4.5": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 2000000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/xai/grok4.6": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 2000000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/xai/grok4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "gmi", + "max_input_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-4.5-Air-FP8": { + "input_cost_per_token": 2e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131076, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-4.5-FP8": { + "input_cost_per_token": 6e-07, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-4.6": { + "input_cost_per_token": 6e-07, + "litellm_provider": "gmi", + "max_input_tokens": 204800, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-4.7-Flash": { + "input_cost_per_token": 7e-08, + "litellm_provider": "gmi", + "max_input_tokens": 202752, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-5-FP8": { + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "gmi", + "max_input_tokens": 202752, + "mode": "chat", + "output_cost_per_token": 1.92e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-5.1-FP8": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "gmi", + "max_input_tokens": 202752, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-5.2-FP8": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-5.3": { + "cache_read_input_token_cost": 1.3e-07, + "input_cost_per_token": 7e-07, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "gmi/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, + "fireworks_ai/accounts/fireworks/models/kimi-k3p1-pro": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_priority": 3e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_priority": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_priority": 1.5e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/moonshotai/Kimi-K3.1-Pro": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1000000, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-image-2.6-sunburst": { + "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_image_token": 8e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_pdf_input": true, + "supports_vision": true + }, + "gpt-image-2.6-flare": { + "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_image_token": 8e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_pdf_input": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/moonshotai.kimi-k3": { + "cache_creation_input_token_cost": 4.95e-06, + "cache_creation_input_token_cost_flex": 2.475e-06, + "cache_creation_input_token_cost_priority": 8.6625e-06, + "cache_read_input_token_cost": 3.96e-07, + "cache_read_input_token_cost_flex": 1.98e-07, + "cache_read_input_token_cost_priority": 6.93e-07, + "input_cost_per_token": 3.96e-06, + "input_cost_per_token_batches": 1.98e-06, + "input_cost_per_token_flex": 1.98e-06, + "input_cost_per_token_priority": 6.93e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 868928, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.98e-05, + "output_cost_per_token_batches": 9.9e-06, + "output_cost_per_token_flex": 9.9e-06, + "output_cost_per_token_priority": 3.465e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "token_count_framing": 64.0, + "token_count_tokenizer": "kimi_k3" + }, + "bedrock/us-gov-west-1/moonshotai.kimi-k3": { + "cache_creation_input_token_cost": 4.95e-06, + "cache_creation_input_token_cost_flex": 2.475e-06, + "cache_creation_input_token_cost_priority": 8.6625e-06, + "cache_read_input_token_cost": 3.96e-07, + "cache_read_input_token_cost_flex": 1.98e-07, + "cache_read_input_token_cost_priority": 6.93e-07, + "input_cost_per_token": 3.96e-06, + "input_cost_per_token_batches": 1.98e-06, + "input_cost_per_token_flex": 1.98e-06, + "input_cost_per_token_priority": 6.93e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 868928, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.98e-05, + "output_cost_per_token_batches": 9.9e-06, + "output_cost_per_token_flex": 9.9e-06, + "output_cost_per_token_priority": 3.465e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "token_count_framing": 64.0, + "token_count_tokenizer": "kimi_k3" + }, + "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { + "deprecation_date": "2026-09-10", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-haiku.md", + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 195904, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-east-1/index.json", + "successor_model": "bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-east-1/xai.grok-4.7": { + "cache_read_input_token_cost": 6.6e-07, + "cache_read_input_token_cost_flex": 3.3e-07, + "cache_read_input_token_cost_priority": 1.155e-06, + "input_cost_per_token": 2.64e-06, + "input_cost_per_token_batches": 1.32e-06, + "input_cost_per_token_flex": 1.32e-06, + "input_cost_per_token_priority": 4.62e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 7.92e-06, + "output_cost_per_token_batches": 3.96e-06, + "output_cost_per_token_flex": 3.96e-06, + "output_cost_per_token_priority": 1.386e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "use_openai_responses_path": true + }, + "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { + "deprecation_date": "2026-09-10", + "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-haiku.md", + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 195904, + "max_output_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json", + "successor_model": "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-west-1/xai.grok-4.7": { + "cache_read_input_token_cost": 6.6e-07, + "cache_read_input_token_cost_flex": 3.3e-07, + "cache_read_input_token_cost_priority": 1.155e-06, + "input_cost_per_token": 2.64e-06, + "input_cost_per_token_batches": 1.32e-06, + "input_cost_per_token_flex": 1.32e-06, + "input_cost_per_token_priority": 4.62e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 7.92e-06, + "output_cost_per_token_batches": 3.96e-06, + "output_cost_per_token_flex": 3.96e-06, + "output_cost_per_token_priority": 1.386e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "use_openai_responses_path": true + }, + "bedrock_mantle/xai.grok-4.7": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_flex": 2.75e-07, + "cache_read_input_token_cost_priority": 9.625e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_flex": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "output_cost_per_token_batches": 3.3e-06, + "output_cost_per_token_flex": 3.3e-06, + "output_cost_per_token_priority": 1.155e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "use_openai_responses_path": true + }, + "bedrock_mantle/grok-latest": { + "alias_of": "bedrock_mantle/xai.grok-4.7" + }, + "together_ai/ricursive-ai/Ripple-65B-Preview": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://api.together.ai/v1/models", + "supports_prompt_caching": true + }, + "vertex_ai/gemini-omni-1.2-flash": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 131072, + "max_output_tokens": 260640, + "mode": "chat", + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "output_cost_per_video_token": 1.2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1beta/interactions" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "video" + ], + "supports_audio_input": false, + "supports_audio_output": false, + "supports_computer_use": false, + "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": false, + "supports_tool_choice": false, + "supports_url_context": false, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": false + }, + "gemini/gemini-omni-1.2-flash": { + "input_cost_per_image_token": 1.5e-06, + "input_cost_per_token": 1.5e-06, + "input_cost_per_video_token": 1.5e-06, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "output_cost_per_video_token": 1.2e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1beta/interactions" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "video", + "audio" + ], + "supports_audio_input": false, + "supports_audio_output": true, + "supports_reasoning": true, + "supports_system_messages": false, + "supports_video_input": true, + "supports_vision": true + }, + "databricks/databricks-kimi-k3-1-pro": { + "cache_creation_input_token_cost": 1.99997e-06, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_token": 1.99997e-06, + "input_dbu_cost_per_token": 2.8571e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "metadata": {"notes":"Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference."}, + "mode": "chat", + "output_cost_per_token": 9.99999e-06, + "output_dbu_cost_per_token": 0.000142857, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "token_count_framing": 100.0 + }, + "moonshotai.kimi-k3.1": { + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_flex": 2.75e-06, + "cache_creation_input_token_cost_priority": 9.625e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_flex": 1.1e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_flex": 2.2e-06, + "input_cost_per_token_priority": 7.7e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 868928, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_flex": 1.1e-05, + "output_cost_per_token_priority": 3.85e-05, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3-1-highspeed.md", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_none_reasoning_effort": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.moonshotai.kimi-k3.1": { + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_flex": 2.75e-06, + "cache_creation_input_token_cost_priority": 9.625e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_flex": 1.1e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_flex": 2.2e-06, + "input_cost_per_token_priority": 7.7e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 868928, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_flex": 1.1e-05, + "output_cost_per_token_priority": 3.85e-05, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3-1-highspeed.md", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_none_reasoning_effort": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "global.moonshotai.kimi-k3.1": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_flex": 2.5e-06, + "cache_creation_input_token_cost_priority": 8.75e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_flex": 2e-06, + "input_cost_per_token_priority": 7e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 868928, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_flex": 1e-05, + "output_cost_per_token_priority": 3.5e-05, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3-1-highspeed.md", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_none_reasoning_effort": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "in.moonshotai.kimi-k3.1": { + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_flex": 2.75e-06, + "cache_creation_input_token_cost_priority": 9.625e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_flex": 1.1e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_flex": 2.2e-06, + "input_cost_per_token_priority": 7.7e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 868928, + "max_output_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_flex": 1.1e-05, + "output_cost_per_token_priority": 3.85e-05, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3-1-highspeed.md", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_none_reasoning_effort": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "wandb/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "azure_ai/cohere-rerank-v5-pro": { + "deprecation_date": "2027-02-12", + "deprecation_source": "https://management.azure.com/subscriptions/{subscriptionId}/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", + "input_cost_per_token": 5e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/cohere-rerank-v5-fast": { + "deprecation_date": "2027-02-12", + "deprecation_source": "https://management.azure.com/subscriptions/{subscriptionId}/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", + "input_cost_per_token": 2e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-realtime-2.1": { + "cache_read_input_audio_token_cost": 4.4e-07, + "cache_read_input_image_token_cost": 5.5e-07, + "cache_read_input_token_cost": 4.4e-07, + "deprecation_date": "2027-06-25", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_audio_token": 3.52e-05, + "input_cost_per_image_token": 5.5e-06, + "input_cost_per_token": 4.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 7.04e-05, + "output_cost_per_token": 2.64e-05, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/us/gpt-realtime-2.1-mini": { + "cache_read_input_audio_token_cost": 3.3e-07, + "cache_read_input_image_token_cost": 8.8e-08, + "cache_read_input_token_cost": 6.6e-08, + "deprecation_date": "2027-06-25", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_audio_token": 1.1e-05, + "input_cost_per_image_token": 8.8e-07, + "input_cost_per_token": 6.6e-07, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 2.2e-05, + "output_cost_per_token": 2.64e-06, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/us/gpt-realtime-1.5": { + "cache_read_input_audio_token_cost": 4.4e-07, + "cache_read_input_image_token_cost": 5.5e-07, + "cache_read_input_token_cost": 4.4e-07, + "deprecation_date": "2027-08-24", + "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "input_cost_per_audio_token": 3.52e-05, + "input_cost_per_image_token": 5.5e-06, + "input_cost_per_token": 4.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 7.04e-05, + "output_cost_per_token": 1.76e-05, + "provider_specific_entry": { + "realtime_ga_only": 1 + }, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "eu.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "eu.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "global.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "global.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us-gov.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us-gov.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "claude-fable-5-2": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "input_cost_per_token_batches": 4e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "output_cost_per_token_batches": 2e-05, + "prompt_cache_min_tokens": 512.0, + "provider_specific_entry": {"us":1.1,"fast":2}, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "supports_anthropic_compaction": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_fast_mode": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_speed": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "bedrock/claude_platform/claude-fable-5-2": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "input_cost_per_token_batches": 4e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "output_cost_per_token_batches": 2e-05, + "prompt_cache_min_tokens": 512.0, + "provider_specific_entry": {"us":1.1}, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing", + "supports_adaptive_thinking": true, + "supports_anthropic_compaction": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "azure_ai/claude-mythos-5-2": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "thinking_always_on": true + }, + "azure_ai/claude-mythos-5-2-fast": { + "cache_creation_input_token_cost": 2e-05, + "cache_creation_input_token_cost_above_1hr": 3.2e-05, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token": 1.6e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 8e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "thinking_always_on": true + }, + "azure_ai/claude-fable-5-2": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "thinking_always_on": true + }, + "azure_ai/claude-fable-5-2-fast": { + "cache_creation_input_token_cost": 2e-05, + "cache_creation_input_token_cost_above_1hr": 3.2e-05, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token": 1.6e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 8e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "thinking_always_on": true + }, + "bedrock/us-gov-east-1/anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "bedrock/us-gov-west-1/anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "github_copilot/claude-fable-5.2": { + "cache_creation_input_token_cost": 1e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": true + }, + "together_ai/elorian-labs/glimpse-1.0": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://api.together.ai/v1/models", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "gemini/gemini-4-carbon": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 1.8e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 1.8e-05, + "prompt_cache_min_tokens": 4096.0, + "rpm": 2000.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "source": "https://aistudio.google.com/docs/pricing#gemini-4-carbon", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_computer_use": true, + "supports_continuation": true, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000.0, + "web_search_billing_unit": "per_query" + }, + "vertex_ai/gemini-4-carbon": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_priority": 1.8e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token": 2e-06, + "input_cost_per_audio_token_batches": 1e-06, + "input_cost_per_audio_token_priority": 3.6e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 1.8e-05, + "prompt_cache_min_tokens": 4096.0, + "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_computer_use": true, + "supports_continuation": true, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "vertex_ai/gemini-4-carbon-cyber-permissive": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token": 4e-06, + "input_cost_per_audio_token_batches": 2e-06, + "input_cost_per_audio_token_priority": 7.2e-06, + "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2e-06, + "input_cost_per_token_priority": 7.2e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 2e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, + "output_cost_per_token_priority": 3.6e-05, + "prompt_cache_min_tokens": 4096.0, + "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_computer_use": false, + "supports_continuation": true, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "github_copilot/gemini-4-carbon": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://github.blog/changelog/2026-11-09-gemini-4-carbon-in-github-copilot", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_vision": true + }, + "fal_ai/alibaba/happy-horse/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/happy-horse/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/happy-horse/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/happy-horse/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/happy-horse/v1.1/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.18, + "output_cost_per_second_1080p": 0.18, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/happy-horse/v1.1/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/happy-horse/v1.1/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.18, + "output_cost_per_second_1080p": 0.18, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/happy-horse/v1.1/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/happy-horse/v1.1/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.18, + "output_cost_per_second_1080p": 0.18, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/happy-horse/v1.1/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/wan-3.0-prime/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_480p": 0.068, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/wan-3.0-prime/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/wan-3.0-prime/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_480p": 0.068, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/wan-3.0-prime/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/wan-3.0-prime/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_480p": 0.068, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/wan-3.0-prime/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/wan-3.0/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.2, + "output_cost_per_second_1080p": 0.2, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/alibaba/wan-3.0/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/wan-3.0/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.2, + "output_cost_per_second_1080p": 0.2, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/alibaba/wan-3.0/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/wan-3.0/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.2, + "output_cost_per_second_1080p": 0.2, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/alibaba/wan-3.0/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/draft-enhance": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.29, + "output_cost_per_second_1080p": 0.29, + "source": "https://fal.ai/models/blackforestlabs/flux-3/draft-enhance", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/edit-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_720p": 0.03, + "source": "https://fal.ai/models/blackforestlabs/flux-3/edit-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/extend-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.41, + "output_cost_per_second_1080p": 0.53, + "output_cost_per_second_720p": 0.41, + "source": "https://fal.ai/models/blackforestlabs/flux-3/extend-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/extend-video/draft": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.12, + "output_cost_per_second_720p": 0.12, + "source": "https://fal.ai/models/blackforestlabs/flux-3/extend-video/draft", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/first-last-frame-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "output_cost_per_second_1080p": 0.29, + "output_cost_per_second_720p": 0.17, + "source": "https://fal.ai/models/blackforestlabs/flux-3/first-last-frame-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/first-last-frame-to-video/draft": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_720p": 0.06, + "source": "https://fal.ai/models/blackforestlabs/flux-3/first-last-frame-to-video/draft", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/image-to-video/draft": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_720p": 0.06, + "source": "https://fal.ai/models/blackforestlabs/flux-3/image-to-video/draft", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/keyframes-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "output_cost_per_second_1080p": 0.29, + "output_cost_per_second_720p": 0.17, + "source": "https://fal.ai/models/blackforestlabs/flux-3/keyframes-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/keyframes-to-video/draft": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_720p": 0.06, + "source": "https://fal.ai/models/blackforestlabs/flux-3/keyframes-to-video/draft", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/klein/base/edit-image/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills blackforestlabs/flux-3/klein/base/edit-image/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/base/edit-image/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/blackforestlabs/flux-3/klein/base/text-to-image/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills blackforestlabs/flux-3/klein/base/text-to-image/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/base/text-to-image/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/blackforestlabs/flux-3/klein/edit-image/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills blackforestlabs/flux-3/klein/edit-image/lora at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.012, + "output_cost_per_pixel": 1.1444091796875e-08, + "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/edit-image/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/blackforestlabs/flux-3/klein/text-to-image/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills blackforestlabs/flux-3/klein/text-to-image/lora at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.012, + "output_cost_per_pixel": 1.1444091796875e-08, + "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/text-to-image/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/blackforestlabs/flux-3/text-to-video/draft": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_720p": 0.06, + "source": "https://fal.ai/models/blackforestlabs/flux-3/text-to-video/draft", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/bria_video_eraser/erase/keypoints": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/bria_video_eraser/erase/keypoints", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/bria_video_eraser/erase/mask": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/bria_video_eraser/erase/mask", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/bria_video_eraser/erase/prompt": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/bria_video_eraser/erase/prompt", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/embed-product": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/embed-product", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/extract-object": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://fal.ai/models/bria/extract-object", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-2/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-bbq-preview/generate": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-bbq-preview/generate", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/bria/fibo-edit-1.5/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit-1.5/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit-1.5/expand": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit-1.5/expand", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit-1.5/product-holding": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit-1.5/product-holding", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit-1.5/virtual-try-on": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit-1.5/virtual-try-on", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/add_object_by_text": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/add_object_by_text", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/blend": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/blend", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/colorize": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/colorize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/erase_by_text": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/erase_by_text", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/relight": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/relight", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/replace_object_by_text": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/replace_object_by_text", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/reseason": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/reseason", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/restore": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/restore", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/restyle": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/restyle", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/rewrite_text": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/rewrite_text", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-edit/sketch_to_colored_image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-edit/sketch_to_colored_image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/fibo-gen-1.5/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-gen-1.5/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/bria/fibo-lite/generate": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.036, + "source": "https://fal.ai/models/bria/fibo-lite/generate", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/bria/fibo/generate": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo/generate", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/bria/genfill/v2": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills bria/genfill/v2 at $0.04 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "output_cost_per_pixel": 3.814697265625e-08, + "source": "https://fal.ai/models/bria/genfill/v2", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/guided-remove-background": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/bria/guided-remove-background", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/increase-resolution": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/increase-resolution", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/product-dimensions": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/product-dimensions", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/replace-background": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/replace-background", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/upscale/creative": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/upscale/creative", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bria/video/background-removal": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/video/background-removal", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/video/background-removal/green-screen-despill": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/bria/video/background-removal/green-screen-despill", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/video/background-removal/realtime": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0042, + "source": "https://fal.ai/models/bria/video/background-removal/realtime", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/video/background-removal/v3": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/bria/video/background-removal/v3", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/video/erase/keypoints": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/video/erase/keypoints", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/video/erase/mask": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/video/erase/mask", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/video/erase/prompt": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/video/erase/prompt", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/video/increase-resolution": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/bria/video/increase-resolution", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/omnihuman/v2": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.105, + "source": "https://fal.ai/models/bytedance/omnihuman/v2", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/fast/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.2419, + "output_cost_per_second_720p": 0.2419, + "source": "https://fal.ai/models/bytedance/seedance-2.0/fast/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/fast/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.2419, + "output_cost_per_second_720p": 0.2419, + "source": "https://fal.ai/models/bytedance/seedance-2.0/fast/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/mini/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.1547, + "output_cost_per_second_480p": 0.0721, + "output_cost_per_second_720p": 0.1547, + "source": "https://fal.ai/models/bytedance/seedance-2.0/mini/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/mini/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.007, + "output_cost_per_second_480p": 0.007, + "source": "https://fal.ai/models/bytedance/seedance-2.0/mini/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/mini/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.1547, + "output_cost_per_second_480p": 0.0721, + "output_cost_per_second_720p": 0.1547, + "source": "https://fal.ai/models/bytedance/seedance-2.0/mini/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/us/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.3034, + "output_cost_per_second_1080p": 0.682, + "output_cost_per_second_720p": 0.3034, + "source": "https://fal.ai/models/bytedance/seedance-2.0/us/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/us/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.37, + "output_cost_per_second_480p": 0.1731, + "output_cost_per_second_720p": 0.37, + "source": "https://fal.ai/models/bytedance/seedance-2.0/us/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.5/us/draft/complete": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 1.164, + "source": "https://fal.ai/models/bytedance/seedance-2.5/us/draft/complete", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.5/us/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.473, + "output_cost_per_second_1080p": 1.164, + "output_cost_per_second_480p": 0.2205, + "output_cost_per_second_720p": 0.473, + "source": "https://fal.ai/models/bytedance/seedance-2.5/us/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.5/us/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.473, + "output_cost_per_second_1080p": 1.164, + "output_cost_per_second_480p": 0.2205, + "output_cost_per_second_720p": 0.473, + "source": "https://fal.ai/models/bytedance/seedance-2.5/us/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedream/v5/flash/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.027, + "source": "https://fal.ai/models/bytedance/seedream/v5/flash/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bytedance/seedream/v5/flash/layerize": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.027, + "source": "https://fal.ai/models/bytedance/seedream/v5/flash/layerize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bytedance/seedream/v5/flash/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.027, + "source": "https://fal.ai/models/bytedance/seedream/v5/flash/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/bytedance/seedream/v5/lite/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://fal.ai/models/bytedance/seedream/v5/lite/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bytedance/seedream/v5/lite/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://fal.ai/models/bytedance/seedream/v5/lite/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/clarityai/crystal-upscaler": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills clarityai/crystal-upscaler at $0.016 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.016, + "output_cost_per_pixel": 1.52587890625e-08, + "source": "https://fal.ai/models/clarityai/crystal-upscaler", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/decart/lucy-2-5/realtime": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://fal.ai/models/decart/lucy-2-5/realtime", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/decart/lucy-2-6/realtime": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://fal.ai/models/decart/lucy-2-6/realtime", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/decart/lucy-restyle": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.01, + "source": "https://fal.ai/models/decart/lucy-restyle", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/decart/lucy2-vton/realtime": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://fal.ai/models/decart/lucy2-vton/realtime", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ai-avatar/multi": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.2, + "source": "https://fal.ai/models/fal-ai/ai-avatar/multi", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ai-avatar/multi-text": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.2, + "source": "https://fal.ai/models/fal-ai/ai-avatar/multi-text", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ai-avatar/single-text": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.2, + "source": "https://fal.ai/models/fal-ai/ai-avatar/single-text", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/bagel": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/fal-ai/bagel", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/bagel/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/fal-ai/bagel/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ben/v2/image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/ben/v2/image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/ben/v2/image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/boogu-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/boogu-image at $0.04 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "output_cost_per_pixel": 3.814697265625e-08, + "source": "https://fal.ai/models/fal-ai/boogu-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/boogu-image/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/boogu-image/edit at $0.04 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "output_cost_per_pixel": 3.814697265625e-08, + "source": "https://fal.ai/models/fal-ai/boogu-image/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bria/background/replace": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/background/replace", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bria/eraser": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/eraser", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bria/expand": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/expand", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bria/genfill": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/genfill", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bria/product-shot": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/product-shot", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bria/reimagine": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/reimagine", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bria/text-to-image/base": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/text-to-image/base", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/bria/text-to-image/fast": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.028, + "source": "https://fal.ai/models/fal-ai/bria/text-to-image/fast", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/bria/text-to-image/hd": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bria/text-to-image/hd", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/bytedance/dreamactor/v2": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/fal-ai/bytedance/dreamactor/v2", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/bytedance/omnihuman": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/fal-ai/bytedance/omnihuman", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/bytedance/omnihuman/v1.5": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.16, + "source": "https://fal.ai/models/fal-ai/bytedance/omnihuman/v1.5", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/bytedance/seedream/v4.5/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bytedance/seedream/v4.5/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bytedance/seedream/v4.5/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/bytedance/seedream/v4.5/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/bytedance/seedream/v4/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/bytedance/seedream/v4/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bytedance/seedream/v4/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/bytedance/seedream/v4/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/clarity-upscaler": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/clarity-upscaler at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/clarity-upscaler", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/codeformer": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/codeformer at $0.0021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0021, + "output_cost_per_pixel": 2.002716064453125e-09, + "source": "https://fal.ai/models/fal-ai/codeformer", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/control-light": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/control-light at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/control-light", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/davinci-magihuman": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/fal-ai/davinci-magihuman", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ddcolor": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/ddcolor at $0.001 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.001, + "output_cost_per_pixel": 9.5367431640625e-10, + "source": "https://fal.ai/models/fal-ai/ddcolor", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/depth-anything-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.04, + "source": "https://fal.ai/models/fal-ai/depth-anything-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/echomimic-v3": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.2, + "source": "https://fal.ai/models/fal-ai/echomimic-v3", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ernie-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/ernie-image at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/ernie-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ernie-image/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/ernie-image/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/ernie-image/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ernie-image/lora/turbo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/ernie-image/lora/turbo at $0.015 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.015, + "output_cost_per_pixel": 1.430511474609375e-08, + "source": "https://fal.ai/models/fal-ai/ernie-image/lora/turbo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ernie-image/turbo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/ernie-image/turbo at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/ernie-image/turbo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/fashn/tryon/v1.5": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.075, + "source": "https://fal.ai/models/fal-ai/fashn/tryon/v1.5", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/fashn/tryon/v1.6": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.075, + "source": "https://fal.ai/models/fal-ai/fashn/tryon/v1.6", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/feynobg": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/feynobg", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ffmpeg-api/compose": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0002, + "source": "https://fal.ai/models/fal-ai/ffmpeg-api/compose", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ffmpeg-api/merge-audio-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0002, + "source": "https://fal.ai/models/fal-ai/ffmpeg-api/merge-audio-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/finegrain-eraser": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.27, + "source": "https://fal.ai/models/fal-ai/finegrain-eraser", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/finegrain-eraser/bbox": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.18, + "source": "https://fal.ai/models/fal-ai/finegrain-eraser/bbox", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/finegrain-eraser/mask": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.13, + "source": "https://fal.ai/models/fal-ai/finegrain-eraser/mask", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/firered-image-edit-v1.1": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/firered-image-edit-v1.1 at $0.0325 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0325, + "output_cost_per_pixel": 3.0994415283203126e-08, + "source": "https://fal.ai/models/fal-ai/firered-image-edit-v1.1", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flashhead": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.005, + "source": "https://fal.ai/models/fal-ai/flashhead", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/flux-1/dev": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/dev at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/dev", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-1/dev/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/dev/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/dev/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-1/dev/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/dev/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/dev/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-1/krea": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/krea at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/krea", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-1/krea/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/krea/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/krea/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-1/krea/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/krea/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/krea/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-1/schnell": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/schnell at $0.003 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.003, + "output_cost_per_pixel": 2.86102294921875e-09, + "source": "https://fal.ai/models/fal-ai/flux-1/schnell", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-1/schnell/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/schnell/redux at $0.003 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.003, + "output_cost_per_pixel": 2.86102294921875e-09, + "source": "https://fal.ai/models/fal-ai/flux-1/schnell/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-1/srpo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/srpo at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/srpo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-1/srpo/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-1/srpo/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-1/srpo/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2 at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.012, + "output_cost_per_pixel": 1.1444091796875e-08, + "source": "https://fal.ai/models/fal-ai/flux-2", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-flex": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-flex at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-flex", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-flex/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-flex/edit at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-flex/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2-lora-gallery/add-background": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/add-background at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/add-background", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2-lora-gallery/apartment-staging": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/apartment-staging at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/apartment-staging", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2-lora-gallery/ballpoint-pen-sketch": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/ballpoint-pen-sketch at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/ballpoint-pen-sketch", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-lora-gallery/digital-comic-art": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/digital-comic-art at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/digital-comic-art", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-lora-gallery/face-to-full-portrait": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/face-to-full-portrait at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/face-to-full-portrait", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2-lora-gallery/hdr-style": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/hdr-style at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/hdr-style", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-lora-gallery/multiple-angles": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/multiple-angles at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/multiple-angles", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2-lora-gallery/realism": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/realism at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/realism", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-lora-gallery/satellite-view-style": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/satellite-view-style at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/satellite-view-style", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-lora-gallery/sepia-vintage": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/sepia-vintage at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/sepia-vintage", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-lora-gallery/virtual-tryon": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/virtual-tryon at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/virtual-tryon", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/edit at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.012, + "output_cost_per_pixel": 1.1444091796875e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/flash": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/flash at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.005, + "output_cost_per_pixel": 4.76837158203125e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/flash", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/flash/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/flash/edit at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.005, + "output_cost_per_pixel": 4.76837158203125e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/flash/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/4b": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.005, + "output_cost_per_pixel": 4.76837158203125e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/klein/4b/base": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/base at $0.009 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.009, + "output_cost_per_pixel": 8.58306884765625e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/base", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/klein/4b/base/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/base/edit at $0.009 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.009, + "output_cost_per_pixel": 8.58306884765625e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/base/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/4b/base/edit/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/base/edit/lora at $0.016 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.016, + "output_cost_per_pixel": 1.52587890625e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/base/edit/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/4b/base/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/base/lora at $0.016 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.016, + "output_cost_per_pixel": 1.52587890625e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/base/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/klein/4b/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/edit at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/4b/edit/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/edit/lora at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/edit/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/4b/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/lora at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/klein/9b": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b at $0.006 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.006, + "output_cost_per_pixel": 5.7220458984375e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/klein/9b/base": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/base at $0.011 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.011, + "output_cost_per_pixel": 1.049041748046875e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/base", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/klein/9b/base/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/base/edit at $0.011 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.011, + "output_cost_per_pixel": 1.049041748046875e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/base/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/9b/base/edit/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/base/edit/lora at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.02, + "output_cost_per_pixel": 1.9073486328125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/base/edit/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/9b/base/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/base/lora at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.02, + "output_cost_per_pixel": 1.9073486328125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/base/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/klein/9b/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/edit at $0.011 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.011, + "output_cost_per_pixel": 1.049041748046875e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/9b/edit/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/edit/lora at $0.015 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.015, + "output_cost_per_pixel": 1.430511474609375e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/edit/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/klein/9b/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/lora at $0.015 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.015, + "output_cost_per_pixel": 1.430511474609375e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/lora at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/lora/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/lora/edit at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "output_cost_per_pixel": 2.002716064453125e-08, + "source": "https://fal.ai/models/fal-ai/flux-2/lora/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2/turbo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/turbo at $0.008 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.008, + "output_cost_per_pixel": 7.62939453125e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/turbo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2/turbo/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-2/turbo/edit at $0.008 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, + "mode": "image_generation", + "output_cost_per_image": 0.008, + "output_cost_per_pixel": 7.62939453125e-09, + "source": "https://fal.ai/models/fal-ai/flux-2/turbo/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-general": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-general at $0.075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.075, + "output_cost_per_pixel": 7.152557373046875e-08, + "source": "https://fal.ai/models/fal-ai/flux-general", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-general/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-general/image-to-image at $0.075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.075, + "output_cost_per_pixel": 7.152557373046875e-08, + "source": "https://fal.ai/models/fal-ai/flux-general/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-general/inpainting": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-general/inpainting at $0.075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.075, + "output_cost_per_pixel": 7.152557373046875e-08, + "source": "https://fal.ai/models/fal-ai/flux-general/inpainting", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-kontext-lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-kontext-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-kontext-lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-kontext-lora/inpaint": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-kontext-lora/inpaint at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-kontext-lora/inpaint", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-kontext-lora/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-kontext-lora/text-to-image at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-kontext-lora/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-kontext/dev": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-kontext/dev at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux-kontext/dev", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-krea-lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-krea-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-krea-lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-krea-lora/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-krea-lora/image-to-image at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-krea-lora/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-krea-lora/inpainting": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-krea-lora/inpainting at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-krea-lora/inpainting", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-krea-lora/stream": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-krea-lora/stream at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-krea-lora/stream", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-lora-canny": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-lora-canny at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-lora-canny", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-lora-fill": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-lora-fill at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-lora-fill", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-lora/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-lora/image-to-image at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-lora/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-lora/inpainting": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-lora/inpainting at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-lora/inpainting", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-lora/stream": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-lora/stream at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-lora/stream", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-pro/kontext": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/flux-pro/kontext", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/kontext/max": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/max", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/kontext/max/multi": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/max/multi", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/kontext/max/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/max/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-pro/kontext/multi": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/multi", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/kontext/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-pro/v1.1-ultra-finetuned": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.07, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1-ultra-finetuned", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-pro/v1.1-ultra/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-pro/v1.1-ultra/redux at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1-ultra/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/v1.1/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-pro/v1.1/redux at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/v1/fill": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-pro/v1/fill at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1/fill", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/v1/fill-finetuned": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-pro/v1/fill-finetuned at $0.06 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.06, + "output_cost_per_pixel": 5.7220458984375e-08, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1/fill-finetuned", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pulid": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-pulid at $0.0333 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0333, + "output_cost_per_pixel": 3.175735473632813e-08, + "source": "https://fal.ai/models/fal-ai/flux-pulid", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-vision-upscaler": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux-vision-upscaler at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.1, + "output_cost_per_pixel": 9.5367431640625e-08, + "source": "https://fal.ai/models/fal-ai/flux-vision-upscaler", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux/dev/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/dev/image-to-image at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/flux/dev/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux/dev/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/dev/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/dev/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux/krea": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/krea at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/krea", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux/krea/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/krea/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/krea/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux/krea/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/krea/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/krea/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux/schnell/redux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/schnell/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/schnell/redux", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux/srpo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/srpo at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/srpo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux/srpo/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/flux/srpo/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/srpo/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/framepack": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0333, + "source": "https://fal.ai/models/fal-ai/framepack", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/framepack/f1": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0333, + "source": "https://fal.ai/models/fal-ai/framepack/f1", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/framepack/flf2v": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0333, + "source": "https://fal.ai/models/fal-ai/framepack/flf2v", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/gemini-25-flash-image/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.0398, + "source": "https://fal.ai/models/fal-ai/gemini-25-flash-image/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/gemini-3-pro-image-preview": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://fal.ai/models/fal-ai/gemini-3-pro-image-preview", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/gemini-3-pro-image-preview/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://fal.ai/models/fal-ai/gemini-3-pro-image-preview/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/gemini-3.1-flash-image-preview": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/gemini-3.1-flash-image-preview", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/gemini-3.1-flash-image-preview/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/gemini-3.1-flash-image-preview/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/glm-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/glm-image at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/glm-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/glm-image/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/glm-image/image-to-image at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/glm-image/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/heygen/avatar3/digital-twin": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.034, + "source": "https://fal.ai/models/fal-ai/heygen/avatar3/digital-twin", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/avatar4/digital-twin": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/heygen/avatar4/digital-twin", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/avatar4/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/heygen/avatar4/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/avatar5/digital-twin": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/heygen/avatar5/digital-twin", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/v2/translate/precision": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/heygen/v2/translate/precision", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/v2/translate/speed": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/fal-ai/heygen/v2/translate/speed", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/v2/video-agent": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.034, + "source": "https://fal.ai/models/fal-ai/heygen/v2/video-agent", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/v3/filler-word-removal": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.01, + "source": "https://fal.ai/models/fal-ai/heygen/v3/filler-word-removal", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/v3/lipsync/precision": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/heygen/v3/lipsync/precision", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/v3/lipsync/speed": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/fal-ai/heygen/v3/lipsync/speed", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/heygen/v3/video-agent": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.034, + "source": "https://fal.ai/models/fal-ai/heygen/v3/video-agent", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/hidream-i1-fast": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hidream-i1-fast at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/hidream-i1-fast", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/hidream-i1-full": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hidream-i1-full at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/hidream-i1-full", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/hidream-i1-full/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hidream-i1-full/image-to-image at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/hidream-i1-full/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/hidream-o1-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hidream-o1-image at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/hidream-o1-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/hidream-o1-image/dev": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hidream-o1-image/dev at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.005, + "output_cost_per_pixel": 4.76837158203125e-09, + "source": "https://fal.ai/models/fal-ai/hidream-o1-image/dev", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/hidream-o1-image/dev/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hidream-o1-image/dev/edit at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.005, + "output_cost_per_pixel": 4.76837158203125e-09, + "source": "https://fal.ai/models/fal-ai/hidream-o1-image/dev/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/hidream-o1-image/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hidream-o1-image/edit at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/hidream-o1-image/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/hunyuan_world": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://fal.ai/models/fal-ai/hunyuan_world", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/hunyuan-image/v2.1/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hunyuan-image/v2.1/text-to-image at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.1, + "output_cost_per_pixel": 9.5367431640625e-08, + "source": "https://fal.ai/models/fal-ai/hunyuan-image/v2.1/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/hunyuan-image/v3/instruct/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hunyuan-image/v3/instruct/edit at $0.09 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.09, + "output_cost_per_pixel": 8.58306884765625e-08, + "source": "https://fal.ai/models/fal-ai/hunyuan-image/v3/instruct/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/hunyuan-image/v3/instruct/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hunyuan-image/v3/instruct/text-to-image at $0.09 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.09, + "output_cost_per_pixel": 8.58306884765625e-08, + "source": "https://fal.ai/models/fal-ai/hunyuan-image/v3/instruct/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/hunyuan-image/v3/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/hunyuan-image/v3/text-to-image at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.1, + "output_cost_per_pixel": 9.5367431640625e-08, + "source": "https://fal.ai/models/fal-ai/hunyuan-image/v3/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/hunyuan-video-v1.5/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.075, + "source": "https://fal.ai/models/fal-ai/hunyuan-video-v1.5/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/hunyuan-video-v1.5/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.075, + "source": "https://fal.ai/models/fal-ai/hunyuan-video-v1.5/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/iclight-v2": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/iclight-v2 at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.1, + "output_cost_per_pixel": 9.5367431640625e-08, + "source": "https://fal.ai/models/fal-ai/iclight-v2", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/id-v2v": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.2, + "source": "https://fal.ai/models/fal-ai/id-v2v", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/id-v2v/relight": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.2, + "source": "https://fal.ai/models/fal-ai/id-v2v/relight", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ideogram/character": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://fal.ai/models/fal-ai/ideogram/character", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/character/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://fal.ai/models/fal-ai/ideogram/character/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/character/remix": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://fal.ai/models/fal-ai/ideogram/character/remix", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/object-removal": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/ideogram/object-removal", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/remove-background": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://fal.ai/models/fal-ai/ideogram/remove-background", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/upscale": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/ideogram/upscale", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/ideogram/v2", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ideogram/v2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/ideogram/v2/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v2/remix": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/ideogram/v2/remix", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v2/turbo": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/ideogram/v2/turbo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ideogram/v2/turbo/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/ideogram/v2/turbo/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v2/turbo/remix": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/ideogram/v2/turbo/remix", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v2a": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/ideogram/v2a", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ideogram/v2a/remix": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/ideogram/v2a/remix", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v2a/turbo": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://fal.ai/models/fal-ai/ideogram/v2a/turbo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ideogram/v2a/turbo/remix": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://fal.ai/models/fal-ai/ideogram/v2a/turbo/remix", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v3/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/ideogram/v3/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v3/generate-transparent": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/ideogram/v3/generate-transparent", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/ideogram/v3/layerize-text": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.09, + "source": "https://fal.ai/models/fal-ai/ideogram/v3/layerize-text", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v3/reframe": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/ideogram/v3/reframe", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v3/remix": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/ideogram/v3/remix", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/ideogram/v3/replace-background": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/ideogram/v3/replace-background", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/age-modify": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/age-modify", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/city-teleport": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/city-teleport", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/expression-change": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/expression-change", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/hair-change": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/hair-change", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/headshot-photo": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/headshot-photo", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/makeup-application": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/makeup-application", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/object-removal": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/object-removal", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/outpaint": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/image-apps-v2/outpaint at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/outpaint", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/perspective": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/perspective", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/photo-restoration": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/photo-restoration", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/photography-effects": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.4, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/photography-effects", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/portrait-enhance": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.4, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/portrait-enhance", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/product-holding": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/product-holding", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/product-photography": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/product-photography", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/relighting": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/relighting", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/style-transfer": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/style-transfer", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/texture-transform": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/texture-transform", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-apps-v2/virtual-try-on": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-apps-v2/virtual-try-on", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/age-progression": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/age-progression", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/baby-version": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/baby-version", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/background-change": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/background-change", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/broccoli-haircut": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/broccoli-haircut", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/cartoonify": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/cartoonify", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/color-correction": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/color-correction", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/expression-change": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/expression-change", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/face-enhancement": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/face-enhancement", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/hair-change": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/hair-change", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/object-removal": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/object-removal", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/photo-restoration": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/photo-restoration", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/plushie-style": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/plushie-style", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/professional-photo": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/professional-photo", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/realism": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/realism", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/reframe": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/reframe", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/retouch": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/retouch", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/scene-composition": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/scene-composition", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/style-transfer": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/style-transfer", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/text-removal": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/text-removal", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/time-of-day": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/time-of-day", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/weather-effect": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/weather-effect", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/wojak-style": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/wojak-style", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image-editing/youtube-thumbnails": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/image-editing/youtube-thumbnails", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/image2svg": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://fal.ai/models/fal-ai/image2svg", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/instant-character": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/instant-character at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.1, + "output_cost_per_pixel": 9.5367431640625e-08, + "source": "https://fal.ai/models/fal-ai/instant-character", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/kling-image/o1": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.028, + "source": "https://fal.ai/models/fal-ai/kling-image/o1", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/kling-image/o3/image-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.028, + "source": "https://fal.ai/models/fal-ai/kling-image/o3/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/kling-image/o3/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.028, + "source": "https://fal.ai/models/fal-ai/kling-image/o3/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/kling-image/v3/image-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.028, + "source": "https://fal.ai/models/fal-ai/kling-image/v3/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/kling-image/v3/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.028, + "source": "https://fal.ai/models/fal-ai/kling-image/v3/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/kling-video/ai-avatar/v2/pro": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.115, + "source": "https://fal.ai/models/fal-ai/kling-video/ai-avatar/v2/pro", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/ai-avatar/v2/standard": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0562, + "source": "https://fal.ai/models/fal-ai/kling-video/ai-avatar/v2/standard", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.112, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/reference-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.112, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/standard/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.084, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/standard/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/standard/reference-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.084, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/standard/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/standard/video-to-video/edit": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.126, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/standard/video-to-video/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/standard/video-to-video/reference": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.126, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/standard/video-to-video/reference", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/video-to-video/edit": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.168, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/video-to-video/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o1/video-to-video/reference": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.168, + "source": "https://fal.ai/models/fal-ai/kling-video/o1/video-to-video/reference", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/4k/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.42, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/4k/reference-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.42, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/4k/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.42, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/4k/video-to-video/edit": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.42, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/video-to-video/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/4k/video-to-video/reference": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.42, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/video-to-video/reference", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/pro/video-to-video/edit": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.168, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/pro/video-to-video/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/pro/video-to-video/reference": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.168, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/pro/video-to-video/reference", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/standard/video-to-video/edit": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.126, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/standard/video-to-video/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/o3/standard/video-to-video/reference": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.126, + "source": "https://fal.ai/models/fal-ai/kling-video/o3/standard/video-to-video/reference", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v1.5/pro/effects": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/kling-video/v1.5/pro/effects", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v1.6/pro/effects": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.098, + "source": "https://fal.ai/models/fal-ai/kling-video/v1.6/pro/effects", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v1.6/standard/effects": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.056, + "source": "https://fal.ai/models/fal-ai/kling-video/v1.6/standard/effects", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v1/pro/ai-avatar": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.115, + "source": "https://fal.ai/models/fal-ai/kling-video/v1/pro/ai-avatar", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v1/standard/ai-avatar": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.0562, + "source": "https://fal.ai/models/fal-ai/kling-video/v1/standard/ai-avatar", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v1/standard/effects": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.045, + "source": "https://fal.ai/models/fal-ai/kling-video/v1/standard/effects", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v2.6/pro/motion-control": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.112, + "source": "https://fal.ai/models/fal-ai/kling-video/v2.6/pro/motion-control", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v2.6/standard/motion-control": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.07, + "source": "https://fal.ai/models/fal-ai/kling-video/v2.6/standard/motion-control", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/4k/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.42, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/4k/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/4k/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.42, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/4k/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/pro/motion-control": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.168, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/pro/motion-control", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/standard/motion-control": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.126, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/standard/motion-control", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/turbo/pro/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/turbo/pro/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/turbo/pro/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/turbo/pro/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/turbo/standard/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.112, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/turbo/standard/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v3/turbo/standard/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.112, + "source": "https://fal.ai/models/fal-ai/kling-video/v3/turbo/standard/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/krea-2/turbo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/krea-2/turbo at $0.008 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.008, + "output_cost_per_pixel": 7.62939453125e-09, + "source": "https://fal.ai/models/fal-ai/krea-2/turbo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/krea-2/turbo/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/krea-2/turbo/lora at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/krea-2/turbo/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/krea-2/turbo/style": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/krea-2/turbo/style at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/krea-2/turbo/style", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/krea-wan-14b/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.025, + "source": "https://fal.ai/models/fal-ai/krea-wan-14b/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/krea-wan-14b/video-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.025, + "source": "https://fal.ai/models/fal-ai/krea-wan-14b/video-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/latentsync": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.005, + "source": "https://fal.ai/models/fal-ai/latentsync", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/leffa/pose-transfer": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/fal-ai/leffa/pose-transfer", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/leffa/virtual-tryon": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/fal-ai/leffa/virtual-tryon", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/lightx/recamera": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/lightx/recamera", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/lightx/relight": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/lightx/relight", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/longcat-image at $0.13 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.13, + "output_cost_per_pixel": 1.239776611328125e-07, + "source": "https://fal.ai/models/fal-ai/longcat-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/longcat-image/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/longcat-image/edit at $0.15 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.15, + "output_cost_per_pixel": 1.430511474609375e-07, + "source": "https://fal.ai/models/fal-ai/longcat-image/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/longcat-video/distilled/image-to-video/480p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.005, + "source": "https://fal.ai/models/fal-ai/longcat-video/distilled/image-to-video/480p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-video/distilled/image-to-video/720p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.01, + "source": "https://fal.ai/models/fal-ai/longcat-video/distilled/image-to-video/720p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-video/distilled/text-to-video/480p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.005, + "source": "https://fal.ai/models/fal-ai/longcat-video/distilled/text-to-video/480p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-video/distilled/text-to-video/720p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.01, + "source": "https://fal.ai/models/fal-ai/longcat-video/distilled/text-to-video/720p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-video/image-to-video/480p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.025, + "source": "https://fal.ai/models/fal-ai/longcat-video/image-to-video/480p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-video/image-to-video/720p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.04, + "source": "https://fal.ai/models/fal-ai/longcat-video/image-to-video/720p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-video/text-to-video/480p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.025, + "source": "https://fal.ai/models/fal-ai/longcat-video/text-to-video/480p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/longcat-video/text-to-video/720p": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.04, + "source": "https://fal.ai/models/fal-ai/longcat-video/text-to-video/720p", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/audio-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/audio-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/extend-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/extend-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.16, 2160p $0.32"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.08, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/image-to-video/fast": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.12, 2160p $0.24"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.06, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/image-to-video/fast", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/reframe": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.2, + "output_cost_per_second_1080p": 0.2, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/reframe", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/retake-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/retake-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.16, 2160p $0.32"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.08, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltx-2.3/text-to-video/fast": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.12, 2160p $0.24"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.06, + "source": "https://fal.ai/models/fal-ai/ltx-2.3/text-to-video/fast", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltxv-13b-098-distilled": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://fal.ai/models/fal-ai/ltxv-13b-098-distilled", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltxv-13b-098-distilled/extend": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://fal.ai/models/fal-ai/ltxv-13b-098-distilled/extend", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltxv-13b-098-distilled/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://fal.ai/models/fal-ai/ltxv-13b-098-distilled/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/ltxv-13b-098-distilled/multiconditioning": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://fal.ai/models/fal-ai/ltxv-13b-098-distilled/multiconditioning", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/lumina-image/v2": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/lumina-image/v2 at $0.075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.075, + "output_cost_per_pixel": 7.152557373046875e-08, + "source": "https://fal.ai/models/fal-ai/lumina-image/v2", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/marigold-v2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/marigold-v2", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/minimax/hailuo-02-fast/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 512p rate; tiers without a catalog field: 512p $0.017"}, + "mode": "video_generation", + "output_cost_per_second": 0.017, + "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02-fast/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/minimax/hailuo-02/pro/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02/pro/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/minimax/hailuo-02/pro/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02/pro/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/minimax/hailuo-02/standard/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.045, + "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02/standard/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/minimax/image-01/subject-reference": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://fal.ai/models/fal-ai/minimax/image-01/subject-reference", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/mmaudio-v2": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.001, + "source": "https://fal.ai/models/fal-ai/mmaudio-v2", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/moss-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/moss-image at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_pixel": 4.76837158203125e-08, + "source": "https://fal.ai/models/fal-ai/moss-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/nafnet/deblur": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/nafnet/deblur at $0.0225 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0225, + "output_cost_per_pixel": 2.1457672119140624e-08, + "source": "https://fal.ai/models/fal-ai/nafnet/deblur", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/nafnet/denoise": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/nafnet/denoise at $0.0225 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0225, + "output_cost_per_pixel": 2.1457672119140624e-08, + "source": "https://fal.ai/models/fal-ai/nafnet/denoise", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/nano-banana-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/nano-banana-2/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/nano-banana-pro/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://fal.ai/models/fal-ai/nano-banana-pro/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/nano-banana/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.0398, + "source": "https://fal.ai/models/fal-ai/nano-banana/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/nucleus-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/nucleus-image at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/nucleus-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/omnigen-v2": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/omnigen-v2 at $0.15 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.15, + "output_cost_per_pixel": 1.430511474609375e-07, + "source": "https://fal.ai/models/fal-ai/omnigen-v2", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/one-to-all-animation/1.3b": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate; tiers without a catalog field: 580p $0.045"}, + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_480p": 0.03, + "output_cost_per_second_720p": 0.06, + "source": "https://fal.ai/models/fal-ai/one-to-all-animation/1.3b", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/one-to-all-animation/14b": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate; tiers without a catalog field: 580p $0.09"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_480p": 0.06, + "output_cost_per_second_720p": 0.12, + "source": "https://fal.ai/models/fal-ai/one-to-all-animation/14b", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/patina": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/patina at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/patina", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/phota/enhance": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.13, + "source": "https://fal.ai/models/fal-ai/phota/enhance", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/blur": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/blur", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/chromatic-aberration": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/chromatic-aberration", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/color-correction": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/color-correction", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/color-tint": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/color-tint", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/desaturate": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/desaturate", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/dissolve": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/dissolve", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/dodge-burn": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/dodge-burn", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/grain": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/grain", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/parabolize": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/parabolize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/sharpen": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/sharpen", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/solarize": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/solarize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/post-processing/vignette": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://fal.ai/models/fal-ai/post-processing/vignette", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.02, + "output_cost_per_pixel": 1.9073486328125e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/qwen-image-2512": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-2512 at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.02, + "output_cost_per_pixel": 1.9073486328125e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-2512", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/qwen-image-2512/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-2512/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-2512/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/qwen-image-edit-2509": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509 at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/add-background": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/add-background at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/add-background", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/face-to-full-portrait": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/face-to-full-portrait at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/face-to-full-portrait", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/group-photo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/group-photo at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/group-photo", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/integrate-product": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/integrate-product at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/integrate-product", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/lighting-restoration": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/lighting-restoration at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/lighting-restoration", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/multiple-angles": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/multiple-angles at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/multiple-angles", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/next-scene": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/next-scene at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/next-scene", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/remove-element": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/remove-element at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/remove-element", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/remove-lighting": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/remove-lighting at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/remove-lighting", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/shirt-design": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/shirt-design at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/shirt-design", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2511": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2511 at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2511", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2511-multiple-angles": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2511-multiple-angles at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2511-multiple-angles", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-2511/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2511/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2511/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/add-background": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/add-background at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/add-background", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/face-to-full-portrait": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/face-to-full-portrait at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/face-to-full-portrait", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/group-photo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/group-photo at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/group-photo", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/integrate-product": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/integrate-product at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/integrate-product", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/lighting-restoration": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/lighting-restoration at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/lighting-restoration", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/multiple-angles": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/multiple-angles at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/multiple-angles", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/next-scene": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/next-scene at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/next-scene", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/remove-element": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/remove-element at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/remove-element", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/remove-lighting": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/remove-lighting at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/remove-lighting", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/shirt-design": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/shirt-design at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/shirt-design", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit/image-to-image at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-edit/inpaint": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image-edit/inpaint at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "output_cost_per_pixel": 2.86102294921875e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image-edit/inpaint", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-layered": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/qwen-image-layered", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image-layered/lora": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/fal-ai/qwen-image-layered/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/qwen-image/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/qwen-image/image-to-image at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.02, + "output_cost_per_pixel": 1.9073486328125e-08, + "source": "https://fal.ai/models/fal-ai/qwen-image/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/recraft/upscale/creative": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.25, + "source": "https://fal.ai/models/fal-ai/recraft/upscale/creative", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/recraft/upscale/crisp": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.004, + "source": "https://fal.ai/models/fal-ai/recraft/upscale/crisp", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/recraft/v4.1/pro/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.21, + "source": "https://fal.ai/models/fal-ai/recraft/v4.1/pro/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4.1/pro/text-to-vector": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.3, + "source": "https://fal.ai/models/fal-ai/recraft/v4.1/pro/text-to-vector", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4.1/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://fal.ai/models/fal-ai/recraft/v4.1/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4.1/text-to-vector": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/recraft/v4.1/text-to-vector", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4.1/utility/pro/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.21, + "source": "https://fal.ai/models/fal-ai/recraft/v4.1/utility/pro/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4.1/utility/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://fal.ai/models/fal-ai/recraft/v4.1/utility/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4/pro/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.25, + "source": "https://fal.ai/models/fal-ai/recraft/v4/pro/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4/pro/text-to-vector": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.3, + "source": "https://fal.ai/models/fal-ai/recraft/v4/pro/text-to-vector", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/recraft/v4/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/v4/text-to-vector": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/recraft/v4/text-to-vector", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/recraft/vectorize": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://fal.ai/models/fal-ai/recraft/vectorize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/sana": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/sana at $0.001 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.001, + "output_cost_per_pixel": 9.5367431640625e-10, + "source": "https://fal.ai/models/fal-ai/sana", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/sana/sprint": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/sana/sprint at $0.0025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0025, + "output_cost_per_pixel": 2.384185791015625e-09, + "source": "https://fal.ai/models/fal-ai/sana/sprint", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/sana/v1.5/1.6b": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/sana/v1.5/1.6b at $0.0075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0075, + "output_cost_per_pixel": 7.152557373046875e-09, + "source": "https://fal.ai/models/fal-ai/sana/v1.5/1.6b", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/sana/v1.5/4.8b": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/sana/v1.5/4.8b at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/sana/v1.5/4.8b", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/seedvr/upscale/image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/seedvr/upscale/image at $0.001 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.001, + "output_cost_per_pixel": 9.5367431640625e-10, + "source": "https://fal.ai/models/fal-ai/seedvr/upscale/image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/seedvr/upscale/image/seamless": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/seedvr/upscale/image/seamless at $0.0025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0025, + "output_cost_per_pixel": 2.384185791015625e-09, + "source": "https://fal.ai/models/fal-ai/seedvr/upscale/image/seamless", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/stable-diffusion-v3-medium": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://fal.ai/models/fal-ai/stable-diffusion-v3-medium", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/stable-diffusion-v35-large": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/stable-diffusion-v35-large at $0.065 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.065, + "output_cost_per_pixel": 6.198883056640625e-08, + "source": "https://fal.ai/models/fal-ai/stable-diffusion-v35-large", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/stepx-edit2": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/stepx-edit2 at $0.2 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.2, + "output_cost_per_pixel": 1.9073486328125e-07, + "source": "https://fal.ai/models/fal-ai/stepx-edit2", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/telestyle-v2": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/telestyle-v2 at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/telestyle-v2", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/uso": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/uso at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.1, + "output_cost_per_pixel": 9.5367431640625e-08, + "source": "https://fal.ai/models/fal-ai/uso", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/vidu/q2/reference-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/fal-ai/vidu/q2/reference-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/vidu/q2/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/fal-ai/vidu/q2/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/vidu/reference-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/fal-ai/vidu/reference-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/wan-22-vace-fun-a14b/depth": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan-22-vace-fun-a14b/depth", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-22-vace-fun-a14b/inpainting": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan-22-vace-fun-a14b/inpainting", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-22-vace-fun-a14b/outpainting": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan-22-vace-fun-a14b/outpainting", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-22-vace-fun-a14b/reframe": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan-22-vace-fun-a14b/reframe", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-25-preview/image-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/wan-25-preview/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/wan-25-preview/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan-25-preview/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-25-preview/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/wan-25-preview/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/wan-25-preview/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan-25-preview/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-14b": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan-vace-14b", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-14b/depth": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan-vace-14b/depth", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-14b/inpainting": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan-vace-14b/inpainting", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-14b/outpainting": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan-vace-14b/outpainting", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-14b/pose": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan-vace-14b/pose", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-14b/reframe": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan-vace-14b/reframe", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-apps/video-edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan-vace-apps/video-edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-14b/speech-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate; tiers without a catalog field: 580p $0.15"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_480p": 0.1, + "output_cost_per_second_720p": 0.2, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-14b/speech-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-5b/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.016, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-5b/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/wan/v2.2-a14b/image-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/wan/v2.2-a14b/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-a14b/image-to-video/lora": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/image-to-video/lora", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-a14b/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/wan/v2.2-a14b/text-to-image/lora": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/text-to-image/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/wan/v2.2-a14b/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-a14b/text-to-video/lora": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/text-to-video/lora", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-a14b/video-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 580p $0.06"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/video-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.7/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/wan/v2.7/edit-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/edit-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.7/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.7/pro/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.075, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/pro/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/wan/v2.7/pro/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.075, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/pro/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/wan/v2.7/reference-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.7/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/wan/v2.7/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/fal-ai/wan/v2.7/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/z-image/base": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/base at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/z-image/base", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/z-image/base/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/base/lora at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.012, + "output_cost_per_pixel": 1.1444091796875e-08, + "source": "https://fal.ai/models/fal-ai/z-image/base/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/z-image/turbo": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.005, + "output_cost_per_pixel": 4.76837158203125e-09, + "source": "https://fal.ai/models/fal-ai/z-image/turbo", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/z-image/turbo/controlnet": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/controlnet at $0.0065 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0065, + "output_cost_per_pixel": 6.198883056640625e-09, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/controlnet", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/z-image/turbo/controlnet/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/controlnet/lora at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/controlnet/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/z-image/turbo/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/image-to-image at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.005, + "output_cost_per_pixel": 4.76837158203125e-09, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/z-image/turbo/image-to-image/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/image-to-image/lora at $0.0085 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0085, + "output_cost_per_pixel": 8.106231689453126e-09, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/image-to-image/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/z-image/turbo/inpaint": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/inpaint at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "output_cost_per_pixel": 9.5367431640625e-09, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/inpaint", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/z-image/turbo/inpaint/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/inpaint/lora at $0.0115 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0115, + "output_cost_per_pixel": 1.0967254638671875e-08, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/inpaint/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/z-image/turbo/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/lora at $0.0085 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0085, + "output_cost_per_pixel": 8.106231689453126e-09, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/z-image/turbo/tiling": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/tiling at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.02, + "output_cost_per_pixel": 1.9073486328125e-08, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/tiling", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/z-image/turbo/tiling/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills fal-ai/z-image/turbo/tiling/lora at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/z-image/turbo/tiling/lora", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.1/edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 360p $0.03"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_4k": 0.3, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.1/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.1/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 360p $0.03"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_4k": 0.3, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.1/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.1/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 360p $0.03"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_4k": 0.3, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.1/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.1/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 360p $0.03"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_4k": 0.3, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.1/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/kling/v4/flash/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.094, + "output_cost_per_second_720p": 0.094, + "source": "https://fal.ai/models/kling/v4/flash/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/kling/v4/flash/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.094, + "output_cost_per_second_720p": 0.094, + "source": "https://fal.ai/models/kling/v4/flash/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/kling/v4/flash/video-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.063, + "output_cost_per_second_720p": 0.063, + "source": "https://fal.ai/models/kling/v4/flash/video-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/kling/v4/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.235, + "output_cost_per_second_1080p": 0.235, + "output_cost_per_second_720p": 0.157, + "source": "https://fal.ai/models/kling/v4/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/kling/v4/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.235, + "output_cost_per_second_1080p": 0.235, + "output_cost_per_second_720p": 0.157, + "source": "https://fal.ai/models/kling/v4/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/kling/v4/video-to-video/edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.141, + "output_cost_per_second_1080p": 0.141, + "output_cost_per_second_720p": 0.094, + "source": "https://fal.ai/models/kling/v4/video-to-video/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/krea/v3/edit": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills krea/v3/edit at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/krea/v3/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/krea/v3/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills krea/v3/text-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/krea/v3/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/luma/agent/uni-1/v1/max": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.102, + "source": "https://fal.ai/models/luma/agent/uni-1/v1/max", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/luma/agent/uni-1/v1/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.042, + "source": "https://fal.ai/models/luma/agent/uni-1/v1/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/meta/muse-image/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://fal.ai/models/meta/muse-image/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/meta/muse-image/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://fal.ai/models/meta/muse-image/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/minimax/h3-max-turbo/extend-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.04, + "output_cost_per_second_1080p": 0.08, + "output_cost_per_second_2k": 0.16, + "output_cost_per_second_480p": 0.025, + "output_cost_per_second_768p": 0.04, + "source": "https://fal.ai/models/minimax/h3-max-turbo/extend-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max-turbo/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.16, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max-turbo/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/extend-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.16, + "output_cost_per_second_2k": 0.32, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/extend-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/insert-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.06, + "source": "https://fal.ai/models/minimax/h3-max/insert-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/lip-sync/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.16, + "output_cost_per_second_2k": 0.32, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/lip-sync/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.13, + "output_cost_per_second_2k": 0.13, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_4k": 0.16, + "output_cost_per_second_768p": 0.06, + "source": "https://fal.ai/models/minimax/h3/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3/image-to-video/lora": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.1625, + "output_cost_per_second_2k": 0.1625, + "output_cost_per_second_480p": 0.0625, + "output_cost_per_second_4k": 0.2, + "output_cost_per_second_768p": 0.075, + "source": "https://fal.ai/models/minimax/h3/image-to-video/lora", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3/reference-to-video/lora": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.1625, + "output_cost_per_second_2k": 0.1625, + "output_cost_per_second_480p": 0.0625, + "output_cost_per_second_4k": 0.2, + "output_cost_per_second_768p": 0.075, + "source": "https://fal.ai/models/minimax/h3/reference-to-video/lora", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3/text-to-video/lora": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.1625, + "output_cost_per_second_2k": 0.1625, + "output_cost_per_second_480p": 0.0625, + "output_cost_per_second_4k": 0.2, + "output_cost_per_second_768p": 0.075, + "source": "https://fal.ai/models/minimax/h3/text-to-video/lora", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/nvidia/cosmos-3-super/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/nvidia/cosmos-3-super/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/pixelcut/background-removal": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.016, + "source": "https://fal.ai/models/pixelcut/background-removal", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/pixelcut/looping-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.32, + "output_cost_per_second_1080p": 0.32, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_768p": 0.16, + "source": "https://fal.ai/models/pixelcut/looping-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/pixelcut/product-photo": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.024, + "source": "https://fal.ai/models/pixelcut/product-photo", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/pixverse/music-video/vibemv": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.09, + "output_cost_per_second_720p": 0.06, + "source": "https://fal.ai/models/pixverse/music-video/vibemv", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/recraft/v4.1/flash/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.007, + "source": "https://fal.ai/models/recraft/v4.1/flash/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/rundiffusion-fal/juggernaut-flux/base": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/base at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/base", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/rundiffusion-fal/juggernaut-flux/base/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/base/image-to-image at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/base/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/rundiffusion-fal/juggernaut-flux/lightning": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/lightning at $0.006 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.006, + "output_cost_per_pixel": 5.7220458984375e-09, + "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/lightning", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/rundiffusion-fal/juggernaut-flux/pro": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/pro at $0.055 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.055, + "output_cost_per_pixel": 5.245208740234375e-08, + "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/pro", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/rundiffusion-fal/juggernaut-flux/pro/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/pro/image-to-image at $0.055 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.055, + "output_cost_per_pixel": 5.245208740234375e-08, + "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/pro/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/rundiffusion-fal/rundiffusion-photo-flux": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills rundiffusion-fal/rundiffusion-photo-flux at $0.045 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.045, + "output_cost_per_pixel": 4.291534423828125e-08, + "source": "https://fal.ai/models/rundiffusion-fal/rundiffusion-photo-flux", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/smoretalk-ai/rembg-enhance": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.006, + "source": "https://fal.ai/models/smoretalk-ai/rembg-enhance", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/sonilo/v1.1/video-to-video-music": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.009, + "source": "https://fal.ai/models/sonilo/v1.1/video-to-video-music", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/sonilo/v1.1/video-to-video-sound-effects": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.009, + "source": "https://fal.ai/models/sonilo/v1.1/video-to-video-sound-effects", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/tbc/mischief-1/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.01, + "output_cost_per_second_480p": 0.005, + "output_cost_per_second_720p": 0.01, + "source": "https://fal.ai/models/tbc/mischief-1/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/veed/fabric-1.0": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p)"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.15, + "source": "https://fal.ai/models/veed/fabric-1.0", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/veed/fabric-1.0/fast": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p)"}, + "mode": "video_generation", + "output_cost_per_second": 0.2, + "output_cost_per_second_480p": 0.1, + "output_cost_per_second_720p": 0.2, + "source": "https://fal.ai/models/veed/fabric-1.0/fast", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/veed/fabric-1.0/text": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p)"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.15, + "source": "https://fal.ai/models/veed/fabric-1.0/text", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/wan/v2.6/image-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/wan/v2.6/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/wan/v2.6/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/wan/v2.6/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/wan/v2.6/image-to-video/flash": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.075, + "output_cost_per_second_1080p": 0.075, + "output_cost_per_second_720p": 0.05, + "source": "https://fal.ai/models/wan/v2.6/image-to-video/flash", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/wan/v2.6/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/wan/v2.6/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/wan/v2.6/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/wan/v2.6/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/wan/v2.6/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/wan/v2.6/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://fal.ai/models/xai/grok-imagine-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/xai/grok-imagine-video/v1.5/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.14, + "output_cost_per_second_1080p": 0.25, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/alibaba/happy-horse/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/alibaba/happy-horse/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/creatify/boreal": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.01, + "output_cost_per_second_1080p": 0.03, + "output_cost_per_second_2k": 0.12, + "output_cost_per_second_720p": 0.01, + "source": "https://fal.ai/models/creatify/boreal", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/creatify/aurora": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.14, + "output_cost_per_second_480p": 0.07, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/fal-ai/creatify/aurora", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/vidu/q4/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 540p $0.0315"}, + "mode": "video_generation", + "output_cost_per_second": 0.0665, + "output_cost_per_second_1080p": 0.084, + "output_cost_per_second_2k": 0.133, + "output_cost_per_second_4k": 0.273, + "output_cost_per_second_720p": 0.0665, + "source": "https://fal.ai/models/fal-ai/vidu/q4/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/vidu/q4/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 540p $0.0315"}, + "mode": "video_generation", + "output_cost_per_second": 0.0665, + "output_cost_per_second_1080p": 0.084, + "output_cost_per_second_2k": 0.133, + "output_cost_per_second_4k": 0.273, + "output_cost_per_second_720p": 0.0665, + "source": "https://fal.ai/models/fal-ai/vidu/q4/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/ideogram/v4.5": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/ideogram/v4.5", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/ideogram/v4.5/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://fal.ai/models/ideogram/v4.5/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/ideogram/v4/instant": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"fal bills ideogram/v4/instant at $0.0075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, + "mode": "image_generation", + "output_cost_per_image": 0.0075, + "output_cost_per_pixel": 7.152557373046875e-09, + "source": "https://fal.ai/models/ideogram/v4/instant", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/lightricks/ltx-2.5/image-to-video/fast": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.19"}, + "mode": "video_generation", + "output_cost_per_second": 0.13, + "output_cost_per_second_1080p": 0.13, + "output_cost_per_second_4k": 0.3, + "output_cost_per_second_720p": 0.09, + "source": "https://fal.ai/models/lightricks/ltx-2.5/image-to-video/fast", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/lightricks/ltx-2.5/image-to-video/pro": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "output_cost_per_second_1080p": 0.17, + "output_cost_per_second_720p": 0.12, + "source": "https://fal.ai/models/lightricks/ltx-2.5/image-to-video/pro", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/lightricks/ltx-2.5/text-to-video/fast": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.19"}, + "mode": "video_generation", + "output_cost_per_second": 0.13, + "output_cost_per_second_1080p": 0.13, + "output_cost_per_second_4k": 0.3, + "output_cost_per_second_720p": 0.09, + "source": "https://fal.ai/models/lightricks/ltx-2.5/text-to-video/fast", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/lightricks/ltx-2.5/text-to-video/pro": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "output_cost_per_second_1080p": 0.17, + "output_cost_per_second_720p": 0.12, + "source": "https://fal.ai/models/lightricks/ltx-2.5/text-to-video/pro", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/recast": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.45, + "output_cost_per_second_1080p": 0.45, + "output_cost_per_second_768p": 0.3, + "source": "https://fal.ai/models/minimax/h3-max/recast", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/reframe-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/reframe-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/relight": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.16, + "output_cost_per_second_2k": 0.32, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/relight", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/wan/v2.6/reference-to-video/flash": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://fal.ai/models/wan/v2.6/reference-to-video/flash", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-video/v1.5/lite/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_1080p": 0.14, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_720p": 0.03, + "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/lite/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-video/v1.5/lite/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_1080p": 0.14, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_720p": 0.03, + "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/lite/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3-max/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; promotional 50% off rate through 2026-11-22 23:59 UTC per the page; regular rates $0.17 (720p) and $0.29 (1080p) per second resume 2026-11-23 00:00 UTC (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.085, + "output_cost_per_second_1080p": 0.145, + "output_cost_per_second_720p": 0.085, + "source": "https://fal.ai/models/blackforestlabs/flux-3-max/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3-max/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; promotional 50% off rate through 2026-11-22 23:59 UTC per the page; regular rates $0.17 (720p) and $0.29 (1080p) per second resume 2026-11-23 00:00 UTC (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.085, + "output_cost_per_second_1080p": 0.145, + "output_cost_per_second_720p": 0.085, + "source": "https://fal.ai/models/blackforestlabs/flux-3-max/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3-max/keyframes-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; regular rate; the page's 75% promotion ran October 15 to November 7, 2026 and has ended (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "output_cost_per_second_1080p": 0.29, + "output_cost_per_second_720p": 0.17, + "source": "https://fal.ai/models/blackforestlabs/flux-3-max/keyframes-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/heygen/heygen-video/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; regular rate; the page's 50% promotion ended October 31, 2026 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.02, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.06, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_768p": 0.02, + "source": "https://fal.ai/models/heygen/heygen-video/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/heygen/heygen-video/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; regular rate; the page's 50% promotion ended October 31, 2026 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.02, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.06, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_768p": 0.02, + "source": "https://fal.ai/models/heygen/heygen-video/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/heygen/heygen-video/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; regular rate; the page's 50% promotion ended October 31, 2026 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.02, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.06, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_768p": 0.02, + "source": "https://fal.ai/models/heygen/heygen-video/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max-turbo/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.025 (480p), $0.04 (768p), $0.08 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.028, + "output_cost_per_second_1080p": 0.056, + "output_cost_per_second_480p": 0.0175, + "output_cost_per_second_768p": 0.028, + "source": "https://fal.ai/models/minimax/h3-max-turbo/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max-turbo/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.025 (480p), $0.04 (768p), $0.08 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.028, + "output_cost_per_second_1080p": 0.056, + "output_cost_per_second_480p": 0.0175, + "output_cost_per_second_768p": 0.028, + "source": "https://fal.ai/models/minimax/h3-max-turbo/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/camera-controls": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.05 (480p), $0.08 (768p), $0.16 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.035, + "output_cost_per_second_1080p": 0.112, + "output_cost_per_second_480p": 0.035, + "output_cost_per_second_768p": 0.056, + "source": "https://fal.ai/models/minimax/h3-max/camera-controls", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.05 (480p), $0.08 (768p), $0.16 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.056, + "output_cost_per_second_1080p": 0.112, + "output_cost_per_second_480p": 0.035, + "output_cost_per_second_768p": 0.056, + "source": "https://fal.ai/models/minimax/h3-max/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.05 (480p), $0.08 (768p), $0.16 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, + "mode": "video_generation", + "output_cost_per_second": 0.056, + "output_cost_per_second_1080p": 0.112, + "output_cost_per_second_480p": 0.035, + "output_cost_per_second_768p": 0.056, + "source": "https://fal.ai/models/minimax/h3-max/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "replicate/alibaba/happyhorse-1.0": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_720p": 0.14, + "source": "https://replicate.com/alibaba/happyhorse-1.0" + }, + "replicate/alibaba/happyhorse-1.1": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.18, + "output_cost_per_second_1080p": 0.18, + "output_cost_per_second_720p": 0.14, + "source": "https://replicate.com/alibaba/happyhorse-1.1" + }, + "replicate/alibaba/qwen-image-3": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/alibaba/qwen-image-3" + }, + "replicate/alibaba/qwen-image-3-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/alibaba/qwen-image-3-pro" + }, + "replicate/alibaba/wan-3": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "output_cost_per_second_1080p": 0.14, + "output_cost_per_second_480p": 0.035, + "output_cost_per_second_720p": 0.07, + "source": "https://replicate.com/alibaba/wan-3" + }, + "replicate/alibaba/wan-3-prime": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.28, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_480p": 0.068, + "output_cost_per_second_720p": 0.14, + "source": "https://replicate.com/alibaba/wan-3-prime" + }, + "replicate/anthropic/claude-fable-5": { + "input_cost_per_token": 1e-05, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://replicate.com/anthropic/claude-fable-5", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/anthropic/claude-fable-5.2": { + "input_cost_per_token": 8e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 4e-05, + "source": "https://replicate.com/anthropic/claude-fable-5.2", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/anthropic/claude-opus-4.6": { + "input_cost_per_token": 5e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://replicate.com/anthropic/claude-opus-4.6", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/anthropic/claude-opus-4.7": { + "input_cost_per_token": 5e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://replicate.com/anthropic/claude-opus-4.7", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/anthropic/claude-opus-5.5": { + "input_cost_per_token": 4e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2e-05, + "source": "https://replicate.com/anthropic/claude-opus-5.5", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/anthropic/claude-sonnet-4.6": { + "input_cost_per_token": 3e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://replicate.com/anthropic/claude-sonnet-4.6", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/anthropic/claude-sonnet-5": { + "input_cost_per_token": 2e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://replicate.com/anthropic/claude-sonnet-5", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/black-forest-labs/flux-1.1-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/black-forest-labs/flux-1.1-pro" + }, + "replicate/black-forest-labs/flux-1.1-pro-ultra": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://replicate.com/black-forest-labs/flux-1.1-pro-ultra" + }, + "replicate/black-forest-labs/flux-1.1-pro-ultra-finetuned": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.07, + "source": "https://replicate.com/black-forest-labs/flux-1.1-pro-ultra-finetuned" + }, + "replicate/black-forest-labs/flux-2-flex": { + "input_cost_per_pixel": 6e-08, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 6e-08, + "source": "https://replicate.com/black-forest-labs/flux-2-flex" + }, + "replicate/black-forest-labs/flux-2-klein-4b": { + "input_cost_per_pixel": 1e-09, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 1e-09, + "source": "https://replicate.com/black-forest-labs/flux-2-klein-4b" + }, + "replicate/black-forest-labs/flux-2-klein-4b-base": { + "input_cost_per_pixel": 9e-09, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 9e-09, + "source": "https://replicate.com/black-forest-labs/flux-2-klein-4b-base" + }, + "replicate/black-forest-labs/flux-2-klein-4b-base-lora": { + "input_cost_per_pixel": 9e-09, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 1.9e-08, + "source": "https://replicate.com/black-forest-labs/flux-2-klein-4b-base-lora" + }, + "replicate/black-forest-labs/flux-2-klein-9b": { + "input_cost_per_pixel": 2e-09, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 1.5e-08, + "source": "https://replicate.com/black-forest-labs/flux-2-klein-9b" + }, + "replicate/black-forest-labs/flux-2-klein-9b-base": { + "input_cost_per_pixel": 1.1e-08, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 1.1e-08, + "source": "https://replicate.com/black-forest-labs/flux-2-klein-9b-base" + }, + "replicate/black-forest-labs/flux-2-klein-9b-base-lora": { + "input_cost_per_pixel": 1.1e-08, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 2.1e-08, + "source": "https://replicate.com/black-forest-labs/flux-2-klein-9b-base-lora" + }, + "replicate/black-forest-labs/flux-canny-dev": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/black-forest-labs/flux-canny-dev" + }, + "replicate/black-forest-labs/flux-canny-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://replicate.com/black-forest-labs/flux-canny-pro" + }, + "replicate/black-forest-labs/flux-depth-dev": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/black-forest-labs/flux-depth-dev" + }, + "replicate/black-forest-labs/flux-depth-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://replicate.com/black-forest-labs/flux-depth-pro" + }, + "replicate/black-forest-labs/flux-dev": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/black-forest-labs/flux-dev" + }, + "replicate/black-forest-labs/flux-dev-lora": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.032, + "source": "https://replicate.com/black-forest-labs/flux-dev-lora" + }, + "replicate/black-forest-labs/flux-fill-dev": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/black-forest-labs/flux-fill-dev" + }, + "replicate/black-forest-labs/flux-fill-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://replicate.com/black-forest-labs/flux-fill-pro" + }, + "replicate/black-forest-labs/flux-kontext-dev": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/black-forest-labs/flux-kontext-dev" + }, + "replicate/black-forest-labs/flux-kontext-dev-lora": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.032, + "source": "https://replicate.com/black-forest-labs/flux-kontext-dev-lora" + }, + "replicate/black-forest-labs/flux-kontext-max": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://replicate.com/black-forest-labs/flux-kontext-max" + }, + "replicate/black-forest-labs/flux-kontext-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/black-forest-labs/flux-kontext-pro" + }, + "replicate/black-forest-labs/flux-krea-dev": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/black-forest-labs/flux-krea-dev" + }, + "replicate/black-forest-labs/flux-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.055, + "source": "https://replicate.com/black-forest-labs/flux-pro" + }, + "replicate/black-forest-labs/flux-pro-finetuned": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://replicate.com/black-forest-labs/flux-pro-finetuned" + }, + "replicate/black-forest-labs/flux-redux-dev": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/black-forest-labs/flux-redux-dev" + }, + "replicate/black-forest-labs/flux-redux-schnell": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.003, + "source": "https://replicate.com/black-forest-labs/flux-redux-schnell" + }, + "replicate/black-forest-labs/flux-schnell": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.003, + "source": "https://replicate.com/black-forest-labs/flux-schnell" + }, + "replicate/black-forest-labs/flux-schnell-lora": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://replicate.com/black-forest-labs/flux-schnell-lora" + }, + "replicate/bria/eraser": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/eraser" + }, + "replicate/bria/expand-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/expand-image" + }, + "replicate/bria/fibo": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/fibo" + }, + "replicate/bria/fibo-edit": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/fibo-edit" + }, + "replicate/bria/generate-background": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/generate-background" + }, + "replicate/bria/genfill": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/genfill" + }, + "replicate/bria/image-3.2": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/image-3.2" + }, + "replicate/bria/increase-resolution": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/increase-resolution" + }, + "replicate/bria/product-cutout": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/product-cutout" + }, + "replicate/bria/product-packshot": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/product-packshot" + }, + "replicate/bria/product-shadow": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bria/product-shadow" + }, + "replicate/bria/remove-background": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.018, + "source": "https://replicate.com/bria/remove-background" + }, + "replicate/bria/video-erase-object": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/bria/video-erase-object" + }, + "replicate/bria/video-increase-resolution": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/bria/video-increase-resolution" + }, + "replicate/bria/video-remove-background": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/bria/video-remove-background" + }, + "replicate/bytedance/dreamactor-m2.0": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/bytedance/dreamactor-m2.0" + }, + "replicate/bytedance/dreamina-3.1": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/bytedance/dreamina-3.1" + }, + "replicate/bytedance/omni-human": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://replicate.com/bytedance/omni-human" + }, + "replicate/bytedance/omni-human-1.5": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.16, + "source": "https://replicate.com/bytedance/omni-human-1.5" + }, + "replicate/bytedance/seedance-1-lite": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.036, + "output_cost_per_second_1080p": 0.072, + "output_cost_per_second_480p": 0.018, + "output_cost_per_second_720p": 0.036, + "source": "https://replicate.com/bytedance/seedance-1-lite" + }, + "replicate/bytedance/seedance-1-pro": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_480p": 0.03, + "output_cost_per_second_720p": 0.06, + "source": "https://replicate.com/bytedance/seedance-1-pro" + }, + "replicate/bytedance/seedance-1-pro-fast": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_480p": 0.015, + "output_cost_per_second_720p": 0.025, + "source": "https://replicate.com/bytedance/seedance-1-pro-fast" + }, + "replicate/bytedance/seedream-3": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/bytedance/seedream-3" + }, + "replicate/bytedance/seedream-4": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/bytedance/seedream-4" + }, + "replicate/bytedance/seedream-4.5": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/bytedance/seedream-4.5" + }, + "replicate/bytedance/seedream-5-lite": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://replicate.com/bytedance/seedream-5-lite" + }, + "replicate/datalab-to/ocr": { + "litellm_provider": "replicate", + "mode": "ocr", + "ocr_cost_per_page": 0.002, + "source": "https://replicate.com/datalab-to/ocr" + }, + "replicate/decart/lucy-edit-2": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.04, + "source": "https://replicate.com/decart/lucy-edit-2" + }, + "replicate/easel/ai-avatars": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://replicate.com/easel/ai-avatars" + }, + "replicate/elevenlabs/dubbing": { + "litellm_provider": "replicate", + "mode": "audio_speech", + "output_cost_per_second": 0.0366667, + "source": "https://replicate.com/elevenlabs/dubbing" + }, + "replicate/elevenlabs/flash-v2.5": { + "input_cost_per_character": 5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/elevenlabs/flash-v2.5" + }, + "replicate/elevenlabs/turbo-v2.5": { + "input_cost_per_character": 5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/elevenlabs/turbo-v2.5" + }, + "replicate/elevenlabs/v2-multilingual": { + "input_cost_per_character": 0.0001, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/elevenlabs/v2-multilingual" + }, + "replicate/elevenlabs/v3": { + "input_cost_per_character": 0.0001, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/elevenlabs/v3" + }, + "replicate/flux-kontext-apps/cartoonify": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/cartoonify" + }, + "replicate/flux-kontext-apps/change-haircut": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/change-haircut" + }, + "replicate/flux-kontext-apps/depth-of-field": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/depth-of-field" + }, + "replicate/flux-kontext-apps/face-to-many-kontext": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/face-to-many-kontext" + }, + "replicate/flux-kontext-apps/filters": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/filters" + }, + "replicate/flux-kontext-apps/iconic-locations": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/iconic-locations" + }, + "replicate/flux-kontext-apps/impossible-scenarios": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/impossible-scenarios" + }, + "replicate/flux-kontext-apps/multi-image-kontext-max": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://replicate.com/flux-kontext-apps/multi-image-kontext-max" + }, + "replicate/flux-kontext-apps/multi-image-kontext-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/multi-image-kontext-pro" + }, + "replicate/flux-kontext-apps/multi-image-list": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://replicate.com/flux-kontext-apps/multi-image-list" + }, + "replicate/flux-kontext-apps/portrait-series": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/portrait-series" + }, + "replicate/flux-kontext-apps/professional-headshot": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/professional-headshot" + }, + "replicate/flux-kontext-apps/restore-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/restore-image" + }, + "replicate/flux-kontext-apps/restyle-video-frame": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/restyle-video-frame" + }, + "replicate/flux-kontext-apps/text-removal": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/flux-kontext-apps/text-removal" + }, + "replicate/google/gemini-2.5-flash-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.039, + "source": "https://replicate.com/google/gemini-2.5-flash-image" + }, + "replicate/google/gemini-3-flash": { + "input_cost_per_token": 5e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://replicate.com/google/gemini-3-flash", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/google/gemini-3.1-flash-tts": { + "input_cost_per_token": 2e-06, + "litellm_provider": "replicate", + "mode": "audio_speech", + "output_cost_per_token": 4e-05, + "source": "https://replicate.com/google/gemini-3.1-flash-tts" + }, + "replicate/google/gemini-3.1-pro": { + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "source": "https://replicate.com/google/gemini-3.1-pro", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/google/gemini-3.5-flash": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 9e-06, + "source": "https://replicate.com/google/gemini-3.5-flash", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/google/gemini-3.8-flash-lite-tts": { + "input_cost_per_token": 5e-07, + "litellm_provider": "replicate", + "mode": "audio_speech", + "output_cost_per_token": 6e-06, + "source": "https://replicate.com/google/gemini-3.8-flash-lite-tts" + }, + "replicate/google/gemini-3.8-flash-tts": { + "input_cost_per_token": 5e-07, + "litellm_provider": "replicate", + "mode": "audio_speech", + "output_cost_per_token": 9e-06, + "source": "https://replicate.com/google/gemini-3.8-flash-tts" + }, + "replicate/google/nano-banana": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.039, + "source": "https://replicate.com/google/nano-banana" + }, + "replicate/google/nano-banana-2": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.067, + "output_cost_per_image_1K": 0.067, + "output_cost_per_image_2K": 0.101, + "output_cost_per_image_4K": 0.151, + "source": "https://replicate.com/google/nano-banana-2" + }, + "replicate/google/nano-banana-2-lite": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.034, + "source": "https://replicate.com/google/nano-banana-2-lite" + }, + "replicate/google/nano-banana-2.1": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_1K": 0.0336, + "output_cost_per_image_2K": 0.0504, + "output_cost_per_image_4K": 0.1134, + "source": "https://replicate.com/google/nano-banana-2.1" + }, + "replicate/google/nano-banana-latest": { + "alias_of": "replicate/google/nano-banana-2.1" + }, + "replicate/heygen/avatar-iv": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.075, + "source": "https://replicate.com/heygen/avatar-iv" + }, + "replicate/heygen/avatar-v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.075, + "source": "https://replicate.com/heygen/avatar-v" + }, + "replicate/heygen/lipsync-precision": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.0667, + "source": "https://replicate.com/heygen/lipsync-precision" + }, + "replicate/heygen/lipsync-speed": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.0333, + "source": "https://replicate.com/heygen/lipsync-speed" + }, + "replicate/heygen/video-agent": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.0333, + "source": "https://replicate.com/heygen/video-agent" + }, + "replicate/ibm-granite/granite-20b-code-instruct-8k": { + "input_cost_per_token": 1e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://replicate.com/ibm-granite/granite-20b-code-instruct-8k", + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-3.0-2b-instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-3.0-2b-instruct", + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-3.0-8b-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-3.0-8b-instruct", + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-3.1-2b-instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-3.1-2b-instruct", + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-3.1-8b-instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-3.1-8b-instruct", + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-3.2-8b-instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-3.2-8b-instruct", + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-4.0-h-small": { + "input_cost_per_token": 6e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-4.0-h-small", + "supports_function_calling": true, + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-4.1-8b": { + "input_cost_per_token": 6e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-4.1-8b", + "supports_function_calling": true, + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-4.2-8b": { + "input_cost_per_token": 6e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-4.2-8b", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-8b-code-instruct-128k": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-8b-code-instruct-128k", + "supports_system_messages": true + }, + "replicate/ibm-granite/granite-speech-3.3-8b": { + "litellm_provider": "replicate", + "mode": "audio_transcription", + "output_cost_per_token": 4.9e-06, + "source": "https://replicate.com/ibm-granite/granite-speech-3.3-8b" + }, + "replicate/ibm-granite/granite-speech-4.1-2b": { + "input_cost_per_token": 3e-08, + "litellm_provider": "replicate", + "mode": "audio_transcription", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-speech-4.1-2b" + }, + "replicate/ibm-granite/granite-vision-3.3-2b": { + "input_cost_per_token": 0.0, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-vision-3.3-2b", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/ibm-granite/granite-vision-4.1-4b": { + "input_cost_per_token": 6e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/ibm-granite/granite-vision-4.1-4b", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/ideogram-ai/ideogram-v2": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://replicate.com/ideogram-ai/ideogram-v2" + }, + "replicate/ideogram-ai/ideogram-v2-turbo": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://replicate.com/ideogram-ai/ideogram-v2-turbo" + }, + "replicate/ideogram-ai/ideogram-v2a": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/ideogram-ai/ideogram-v2a" + }, + "replicate/ideogram-ai/ideogram-v2a-turbo": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/ideogram-ai/ideogram-v2a-turbo" + }, + "replicate/ideogram-ai/ideogram-v3-balanced": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://replicate.com/ideogram-ai/ideogram-v3-balanced" + }, + "replicate/ideogram-ai/ideogram-v3-quality": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.09, + "source": "https://replicate.com/ideogram-ai/ideogram-v3-quality" + }, + "replicate/ideogram-ai/ideogram-v3-turbo": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/ideogram-ai/ideogram-v3-turbo" + }, + "replicate/ideogram-ai/ideogram-v4-balanced": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://replicate.com/ideogram-ai/ideogram-v4-balanced" + }, + "replicate/ideogram-ai/ideogram-v4-quality": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://replicate.com/ideogram-ai/ideogram-v4-quality" + }, + "replicate/ideogram-ai/layerize": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.09, + "source": "https://replicate.com/ideogram-ai/layerize" + }, + "replicate/intelligent-utilities/html-to-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.001, + "source": "https://replicate.com/intelligent-utilities/html-to-image" + }, + "replicate/inworld/realtime-tts-1.5-max": { + "input_cost_per_character": 3.5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/inworld/realtime-tts-1.5-max" + }, + "replicate/inworld/realtime-tts-1.5-mini": { + "input_cost_per_character": 1.5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/inworld/realtime-tts-1.5-mini" + }, + "replicate/inworld/realtime-tts-2": { + "input_cost_per_character": 2.5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/inworld/realtime-tts-2" + }, + "replicate/kwaivgi/kling-lip-sync": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.014, + "source": "https://replicate.com/kwaivgi/kling-lip-sync" + }, + "replicate/kwaivgi/kling-v2.1-master": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.28, + "source": "https://replicate.com/kwaivgi/kling-v2.1-master" + }, + "replicate/kwaivgi/kling-v2.5-turbo-pro": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.07, + "source": "https://replicate.com/kwaivgi/kling-v2.5-turbo-pro" + }, + "replicate/lightricks/audio-to-video": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://replicate.com/lightricks/audio-to-video" + }, + "replicate/lightricks/ltx-2-distilled": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://replicate.com/lightricks/ltx-2-distilled" + }, + "replicate/lightricks/ltx-2-fast": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.04, + "output_cost_per_second_1080p": 0.04, + "output_cost_per_second_2k": 0.08, + "output_cost_per_second_4k": 0.16, + "source": "https://replicate.com/lightricks/ltx-2-fast" + }, + "replicate/lightricks/ltx-2-pro": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.12, + "output_cost_per_second_4k": 0.24, + "source": "https://replicate.com/lightricks/ltx-2-pro" + }, + "replicate/lightricks/ltx-2-retake": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://replicate.com/lightricks/ltx-2-retake" + }, + "replicate/lightricks/ltx-2.3-fast": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.12, + "output_cost_per_second_4k": 0.24, + "source": "https://replicate.com/lightricks/ltx-2.3-fast" + }, + "replicate/lightricks/ltx-2.3-pro": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.08, + "output_cost_per_second_2k": 0.16, + "output_cost_per_second_4k": 0.32, + "source": "https://replicate.com/lightricks/ltx-2.3-pro" + }, + "replicate/lightricks/ltx-2.5-fast": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.12, + "output_cost_per_second_4k": 0.24, + "output_cost_per_second_720p": 0.03, + "source": "https://replicate.com/lightricks/ltx-2.5-fast" + }, + "replicate/luma/photon": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/luma/photon" + }, + "replicate/luma/photon-flash": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://replicate.com/luma/photon-flash" + }, + "replicate/luma/reframe-video": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.06, + "source": "https://replicate.com/luma/reframe-video" + }, + "replicate/meta/llama-4-maverick-instruct": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 9.5e-07, + "source": "https://replicate.com/meta/llama-4-maverick-instruct", + "supports_system_messages": true + }, + "replicate/meta/llama-4-scout-instruct": { + "input_cost_per_token": 1.7e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 6.5e-07, + "source": "https://replicate.com/meta/llama-4-scout-instruct", + "supports_system_messages": true + }, + "replicate/meta/llama-guard-4-12b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://replicate.com/meta/llama-guard-4-12b", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/meta/meta-llama-3-70b": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "source": "https://replicate.com/meta/meta-llama-3-70b" + }, + "replicate/meta/meta-llama-3-70b-instruct": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "source": "https://replicate.com/meta/meta-llama-3-70b-instruct", + "supports_system_messages": true + }, + "replicate/meta/meta-llama-3-8b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/meta/meta-llama-3-8b" + }, + "replicate/meta/meta-llama-3-8b-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://replicate.com/meta/meta-llama-3-8b-instruct", + "supports_system_messages": true + }, + "replicate/minimax/h3": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.13, + "output_cost_per_second_2k": 0.13, + "output_cost_per_second_768p": 0.08, + "source": "https://replicate.com/minimax/h3" + }, + "replicate/minimax/h3-highspeed": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.03, + "source": "https://replicate.com/minimax/h3-highspeed" + }, + "replicate/minimax/h3-lite": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "output_cost_per_second_480p": 0.0125, + "output_cost_per_second_768p": 0.02, + "source": "https://replicate.com/minimax/h3-lite" + }, + "replicate/minimax/image-01": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://replicate.com/minimax/image-01" + }, + "replicate/minimax/speech-02-hd": { + "input_cost_per_token": 0.0001, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/minimax/speech-02-hd" + }, + "replicate/minimax/speech-02-turbo": { + "input_cost_per_token": 6e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/minimax/speech-02-turbo" + }, + "replicate/minimax/speech-2.6-hd": { + "input_cost_per_token": 0.0001, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/minimax/speech-2.6-hd" + }, + "replicate/minimax/speech-2.6-turbo": { + "input_cost_per_token": 6e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/minimax/speech-2.6-turbo" + }, + "replicate/minimax/speech-2.8-hd": { + "input_cost_per_token": 0.0001, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/minimax/speech-2.8-hd" + }, + "replicate/minimax/speech-2.8-turbo": { + "input_cost_per_token": 6e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/minimax/speech-2.8-turbo" + }, + "replicate/moonshotai/kimi-k2-thinking": { + "input_cost_per_token": 6.6e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.7e-06, + "source": "https://replicate.com/moonshotai/kimi-k2-thinking" + }, + "replicate/moonshotai/kimi-k2.5": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "source": "https://replicate.com/moonshotai/kimi-k2.5", + "supports_vision": true + }, + "replicate/moonshotai/kimi-k2.6": { + "input_cost_per_token": 9.5e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://replicate.com/moonshotai/kimi-k2.6", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/nightmareai/real-esrgan": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.002, + "source": "https://replicate.com/nightmareai/real-esrgan" + }, + "replicate/openai/gpt-4o-mini-transcribe": { + "input_cost_per_token": 3e-06, + "litellm_provider": "replicate", + "mode": "audio_transcription", + "output_cost_per_token": 5e-06, + "source": "https://replicate.com/openai/gpt-4o-mini-transcribe" + }, + "replicate/openai/gpt-4o-transcribe": { + "input_cost_per_token": 6e-06, + "litellm_provider": "replicate", + "mode": "audio_transcription", + "output_cost_per_token": 1e-05, + "source": "https://replicate.com/openai/gpt-4o-transcribe" + }, + "replicate/openai/gpt-5-pro": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 0.00012, + "source": "https://replicate.com/openai/gpt-5-pro", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/openai/gpt-5.1": { + "input_cost_per_token": 1.25e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://replicate.com/openai/gpt-5.1", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/openai/gpt-5.2": { + "input_cost_per_token": 1.75e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "source": "https://replicate.com/openai/gpt-5.2", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/openai/gpt-5.4": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://replicate.com/openai/gpt-5.4", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/openai/gpt-5.6-luna": { + "input_cost_per_token": 1e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://replicate.com/openai/gpt-5.6-luna", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/openai/gpt-5.6-sol": { + "input_cost_per_token": 2e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://replicate.com/openai/gpt-5.6-sol", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/openai/gpt-5.6-terra": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://replicate.com/openai/gpt-5.6-terra", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/perceptron-ai-inc/isaac-0.1": { + "input_cost_per_token": 2.6e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2.17e-06, + "source": "https://replicate.com/perceptron-ai-inc/isaac-0.1", + "supports_vision": true + }, + "replicate/philz1337x/clarity-pro-upscaler": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_pixel": 3e-08, + "source": "https://replicate.com/philz1337x/clarity-pro-upscaler" + }, + "replicate/pixverse/lipsync": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.04, + "source": "https://replicate.com/pixverse/lipsync" + }, + "replicate/playht/play-dialog": { + "litellm_provider": "replicate", + "mode": "audio_speech", + "output_cost_per_second": 0.001, + "source": "https://replicate.com/playht/play-dialog" + }, + "replicate/prunaai/flux-fast": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://replicate.com/prunaai/flux-fast" + }, + "replicate/prunaai/flux-kontext-fast": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://replicate.com/prunaai/flux-kontext-fast" + }, + "replicate/prunaai/hidream-l1-fast": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://replicate.com/prunaai/hidream-l1-fast" + }, + "replicate/prunaai/p-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://replicate.com/prunaai/p-image" + }, + "replicate/prunaai/p-image-edit": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://replicate.com/prunaai/p-image-edit" + }, + "replicate/prunaai/p-image-edit-lora": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://replicate.com/prunaai/p-image-edit-lora" + }, + "replicate/prunaai/p-image-lora": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://replicate.com/prunaai/p-image-lora" + }, + "replicate/prunaai/p-video-2-pro-avatar": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.04, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.08, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_4k": 0.12, + "output_cost_per_second_768p": 0.04, + "source": "https://replicate.com/prunaai/p-video-2-pro-avatar" + }, + "replicate/prunaai/p-video-2-pro-replace": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_2k": 0.07, + "output_cost_per_second_480p": 0.025, + "output_cost_per_second_4k": 0.09, + "output_cost_per_second_768p": 0.05, + "source": "https://replicate.com/prunaai/p-video-2-pro-replace" + }, + "replicate/prunaai/p-video-animate": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_720p": 0.03, + "source": "https://replicate.com/prunaai/p-video-animate" + }, + "replicate/prunaai/p-video-avatar": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.025, + "output_cost_per_second_1080p": 0.045, + "output_cost_per_second_720p": 0.025, + "source": "https://replicate.com/prunaai/p-video-avatar" + }, + "replicate/prunaai/p-video-replace": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_1080p": 0.06, + "output_cost_per_second_720p": 0.03, + "source": "https://replicate.com/prunaai/p-video-replace" + }, + "replicate/prunaai/wan-2.2-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://replicate.com/prunaai/wan-2.2-image" + }, + "replicate/quiverai/arrow-1.1": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.2, + "source": "https://replicate.com/quiverai/arrow-1.1" + }, + "replicate/quiverai/arrow-1.1-max": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.25, + "source": "https://replicate.com/quiverai/arrow-1.1-max" + }, + "replicate/quiverai/arrow-1.1-max-vectorize": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.2, + "source": "https://replicate.com/quiverai/arrow-1.1-max-vectorize" + }, + "replicate/quiverai/arrow-1.1-vectorize": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.15, + "source": "https://replicate.com/quiverai/arrow-1.1-vectorize" + }, + "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-fusion": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-fusion" + }, + "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-next-scene": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-next-scene" + }, + "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-photo-to-anime": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-photo-to-anime" + }, + "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-relight": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-relight" + }, + "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-skin": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-skin" + }, + "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-upscale": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-upscale" + }, + "replicate/qwen/qwen-edit-multiangle": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen/qwen-edit-multiangle" + }, + "replicate/qwen/qwen-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/qwen/qwen-image" + }, + "replicate/qwen/qwen-image-2": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://replicate.com/qwen/qwen-image-2" + }, + "replicate/qwen/qwen-image-2-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.075, + "source": "https://replicate.com/qwen/qwen-image-2-pro" + }, + "replicate/qwen/qwen-image-2512": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://replicate.com/qwen/qwen-image-2512" + }, + "replicate/qwen/qwen-image-edit": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen/qwen-image-edit" + }, + "replicate/qwen/qwen-image-edit-2511": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen/qwen-image-edit-2511" + }, + "replicate/qwen/qwen-image-edit-plus": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen/qwen-image-edit-plus" + }, + "replicate/qwen/qwen-image-edit-plus-lora": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/qwen/qwen-image-edit-plus-lora" + }, + "replicate/qwen/qwen3-7-plus": { + "input_cost_per_token": 2.76e-07, + "input_cost_per_token_above_256k_tokens": 8.26e-07, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 1.101e-06, + "output_cost_per_token_above_256k_tokens": 3.301e-06, + "source": "https://replicate.com/qwen/qwen3-7-plus", + "supports_system_messages": true, + "supports_vision": true + }, + "replicate/qwen/qwen3-tts": { + "input_cost_per_character": 2e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/qwen/qwen3-tts" + }, + "replicate/recraft-ai/recraft-20b": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.022, + "source": "https://replicate.com/recraft-ai/recraft-20b" + }, + "replicate/recraft-ai/recraft-20b-svg": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.044, + "source": "https://replicate.com/recraft-ai/recraft-20b-svg" + }, + "replicate/recraft-ai/recraft-creative-upscale": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.3, + "source": "https://replicate.com/recraft-ai/recraft-creative-upscale" + }, + "replicate/recraft-ai/recraft-crisp-upscale": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.006, + "source": "https://replicate.com/recraft-ai/recraft-crisp-upscale" + }, + "replicate/recraft-ai/recraft-remove-background": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://replicate.com/recraft-ai/recraft-remove-background" + }, + "replicate/recraft-ai/recraft-v3": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/recraft-ai/recraft-v3" + }, + "replicate/recraft-ai/recraft-v3-svg": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://replicate.com/recraft-ai/recraft-v3-svg" + }, + "replicate/recraft-ai/recraft-v4": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/recraft-ai/recraft-v4" + }, + "replicate/recraft-ai/recraft-v4-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.25, + "source": "https://replicate.com/recraft-ai/recraft-v4-pro" + }, + "replicate/recraft-ai/recraft-v4-pro-svg": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.3, + "source": "https://replicate.com/recraft-ai/recraft-v4-pro-svg" + }, + "replicate/recraft-ai/recraft-v4-styles-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://replicate.com/recraft-ai/recraft-v4-styles-pro" + }, + "replicate/recraft-ai/recraft-v4-styles-pro-svg": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.12, + "source": "https://replicate.com/recraft-ai/recraft-v4-styles-pro-svg" + }, + "replicate/recraft-ai/recraft-v4-svg": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://replicate.com/recraft-ai/recraft-v4-svg" + }, + "replicate/recraft-ai/recraft-v4.1": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/recraft-ai/recraft-v4.1" + }, + "replicate/recraft-ai/recraft-v4.1-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.25, + "source": "https://replicate.com/recraft-ai/recraft-v4.1-pro" + }, + "replicate/recraft-ai/recraft-v4.1-pro-svg": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.25, + "source": "https://replicate.com/recraft-ai/recraft-v4.1-pro-svg" + }, + "replicate/recraft-ai/recraft-v4.1-svg": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/recraft-ai/recraft-v4.1-svg" + }, + "replicate/recraft-ai/recraft-v4.1-utility": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/recraft-ai/recraft-v4.1-utility" + }, + "replicate/recraft-ai/recraft-v4.1-utility-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.25, + "source": "https://replicate.com/recraft-ai/recraft-v4.1-utility-pro" + }, + "replicate/recraft-ai/recraft-vectorize": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://replicate.com/recraft-ai/recraft-vectorize" + }, + "replicate/resemble-ai/chatterbox": { + "input_cost_per_character": 2.5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/resemble-ai/chatterbox" + }, + "replicate/resemble-ai/chatterbox-pro": { + "input_cost_per_character": 4e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/resemble-ai/chatterbox-pro" + }, + "replicate/resemble-ai/chatterbox-turbo": { + "input_cost_per_character": 2.5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/resemble-ai/chatterbox-turbo" + }, + "replicate/retro-diffusion/rd-animation": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.07, + "source": "https://replicate.com/retro-diffusion/rd-animation" + }, + "replicate/runwayml/aleph-2": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.336, + "source": "https://replicate.com/runwayml/aleph-2" + }, + "replicate/runwayml/gen-4.5": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.12, + "source": "https://replicate.com/runwayml/gen-4.5" + }, + "replicate/runwayml/gen4-image-turbo": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/runwayml/gen4-image-turbo" + }, + "replicate/runwayml/gen4-turbo": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/runwayml/gen4-turbo" + }, + "replicate/snowflake/snowflake-arctic-instruct": { + "input_cost_per_token": 2e-05, + "litellm_provider": "replicate", + "mode": "chat", + "output_cost_per_token": 2e-05, + "source": "https://replicate.com/snowflake/snowflake-arctic-instruct", + "supports_system_messages": true + }, + "replicate/stability-ai/stable-diffusion-3": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://replicate.com/stability-ai/stable-diffusion-3" + }, + "replicate/stability-ai/stable-diffusion-3.5-large": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.065, + "source": "https://replicate.com/stability-ai/stable-diffusion-3.5-large" + }, + "replicate/stability-ai/stable-diffusion-3.5-large-turbo": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://replicate.com/stability-ai/stable-diffusion-3.5-large-turbo" + }, + "replicate/stability-ai/stable-diffusion-3.5-medium": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://replicate.com/stability-ai/stable-diffusion-3.5-medium" + }, + "replicate/sync/lipsync-2": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/sync/lipsync-2" + }, + "replicate/sync/lipsync-2-pro": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.08325, + "source": "https://replicate.com/sync/lipsync-2-pro" + }, + "replicate/sync/react-1": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.167, + "source": "https://replicate.com/sync/react-1" + }, + "replicate/tencent/hunyuan-image-2.1": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://replicate.com/tencent/hunyuan-image-2.1" + }, + "replicate/tencent/hunyuan-image-3": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://replicate.com/tencent/hunyuan-image-3" + }, + "replicate/veed/fabric-1.0": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.15, + "source": "https://replicate.com/veed/fabric-1.0" + }, + "replicate/wan-video/wan-2.2-s2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "source": "https://replicate.com/wan-video/wan-2.2-s2v" + }, + "replicate/wan-video/wan-2.5-i2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://replicate.com/wan-video/wan-2.5-i2v" + }, + "replicate/wan-video/wan-2.5-i2v-fast": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.068, + "output_cost_per_second_1080p": 0.102, + "output_cost_per_second_720p": 0.068, + "source": "https://replicate.com/wan-video/wan-2.5-i2v-fast" + }, + "replicate/wan-video/wan-2.5-t2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "source": "https://replicate.com/wan-video/wan-2.5-t2v" + }, + "replicate/wan-video/wan-2.5-t2v-fast": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.068, + "output_cost_per_second_1080p": 0.102, + "output_cost_per_second_720p": 0.068, + "source": "https://replicate.com/wan-video/wan-2.5-t2v-fast" + }, + "replicate/wan-video/wan-2.6-i2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://replicate.com/wan-video/wan-2.6-i2v" + }, + "replicate/wan-video/wan-2.6-t2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://replicate.com/wan-video/wan-2.6-t2v" + }, + "replicate/wan-video/wan-2.7-i2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_720p": 0.1, + "source": "https://replicate.com/wan-video/wan-2.7-i2v" + }, + "replicate/wan-video/wan-2.7-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/wan-video/wan-2.7-image" + }, + "replicate/wan-video/wan-2.7-image-pro": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://replicate.com/wan-video/wan-2.7-image-pro" + }, + "replicate/wan-video/wan-2.7-r2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://replicate.com/wan-video/wan-2.7-r2v" + }, + "replicate/wan-video/wan-2.7-t2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://replicate.com/wan-video/wan-2.7-t2v" + }, + "replicate/wan-video/wan-2.7-videoedit": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://replicate.com/wan-video/wan-2.7-videoedit" + }, + "replicate/wan-video/wan2.6-i2v-flash": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "output_cost_per_second_1080p": 0.075, + "output_cost_per_second_720p": 0.05, + "source": "https://replicate.com/wan-video/wan2.6-i2v-flash" + }, + "replicate/wavespeedai/qwen-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.025, + "source": "https://replicate.com/wavespeedai/qwen-image" + }, + "replicate/wavespeedai/wan-2.1-i2v-480p": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.09, + "source": "https://replicate.com/wavespeedai/wan-2.1-i2v-480p" + }, + "replicate/wavespeedai/wan-2.1-i2v-720p": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.25, + "source": "https://replicate.com/wavespeedai/wan-2.1-i2v-720p" + }, + "replicate/wavespeedai/wan-2.1-t2v-480p": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.07, + "source": "https://replicate.com/wavespeedai/wan-2.1-t2v-480p" + }, + "replicate/wavespeedai/wan-2.1-t2v-720p": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.24, + "source": "https://replicate.com/wavespeedai/wan-2.1-t2v-720p" + }, + "replicate/xai/grok-imagine-image": { + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://replicate.com/xai/grok-imagine-image" + }, + "replicate/xai/grok-imagine-image-quality": { + "input_cost_per_pixel": 1e-08, + "litellm_provider": "replicate", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://replicate.com/xai/grok-imagine-image-quality" + }, + "replicate/xai/grok-imagine-r2v": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/xai/grok-imagine-r2v" + }, + "replicate/xai/grok-imagine-video": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.07, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.07, + "source": "https://replicate.com/xai/grok-imagine-video" + }, + "replicate/xai/grok-imagine-video-1.5": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "source": "https://replicate.com/xai/grok-imagine-video-1.5" + }, + "replicate/xai/grok-imagine-video-extension": { + "litellm_provider": "replicate", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://replicate.com/xai/grok-imagine-video-extension" + }, + "replicate/xai/grok-text-to-speech": { + "input_cost_per_character": 1.5e-05, + "litellm_provider": "replicate", + "mode": "audio_speech", + "source": "https://replicate.com/xai/grok-text-to-speech" + }, + "fal_ai/blackforestlabs/flux-3/edit-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"the page states only the 1K (1 MP) price of $0.048 and the pricing API bills in megapixels at $0.048, so the per-pixel rate is $0.048 per megapixel and the per-image price is the default 1k output; 768sq, 1.5k, 2k and 4k outputs are priced by the per-pixel rate"}, + "mode": "image_generation", + "output_cost_per_image": 0.048, + "output_cost_per_pixel": 4.57763671875e-08, + "source": "https://fal.ai/models/blackforestlabs/flux-3/edit-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/blackforestlabs/flux-3/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; the pricing API reports a $0.085 per second base price that the page does not state"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "output_cost_per_second_1080p": 0.29, + "output_cost_per_second_2k": 0.32, + "output_cost_per_second_4k": 0.47, + "output_cost_per_second_720p": 0.17, + "source": "https://fal.ai/models/blackforestlabs/flux-3/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-3/klein/edit-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per output image by resolution; output_cost_per_image is the 1K rate (image_size defaults to the input size, 1K is the page example); 768 x 768 is $0.008 and 1.5K is $0.011 per image, no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.009, + "output_cost_per_image_1K": 0.009, + "output_cost_per_image_2K": 0.014, + "output_cost_per_image_4K": 0.036, + "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/edit-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/blackforestlabs/flux-3/klein/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per output image by resolution; output_cost_per_image is the 1K rate (default image_size square_hd); 768 x 768 is $0.008 and 1.5K is $0.011 per image, no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.009, + "output_cost_per_image_1K": 0.009, + "output_cost_per_image_2K": 0.014, + "output_cost_per_image_4K": 0.036, + "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/blackforestlabs/flux-3/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"the page states only the 1K (1 MP) price of $0.048 and the pricing API bills in megapixels at $0.048, so the per-pixel rate is $0.048 per megapixel and the per-image price is the default 1k output; 768sq, 1.5k, 2k and 4k outputs are priced by the per-pixel rate"}, + "mode": "image_generation", + "output_cost_per_image": 0.048, + "output_cost_per_pixel": 4.57763671875e-08, + "source": "https://fal.ai/models/blackforestlabs/flux-3/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/blackforestlabs/flux-3/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; the pricing API reports a $0.085 per second base price that the page does not state"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "output_cost_per_second_1080p": 0.29, + "output_cost_per_second_2k": 0.32, + "output_cost_per_second_4k": 0.47, + "output_cost_per_second_720p": 0.17, + "source": "https://fal.ai/models/blackforestlabs/flux-3/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/blackforestlabs/flux-video-upscale": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution in the default creative mode (creativity=1); output_cost_per_second is the highest tier (4K) because the output resolution depends on the source and upscale_factor; precise mode (creativity=0) is $0.084 (1080p), $0.15 (2K) and $0.33 (4K) per second and has no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.474, + "output_cost_per_second_1080p": 0.12, + "output_cost_per_second_2k": 0.21, + "output_cost_per_second_4k": 0.474, + "source": "https://fal.ai/models/blackforestlabs/flux-video-upscale", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bria/fibo-2/generate": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per generated image at the default 1MP output; the 4MP output is $0.06 per image and has no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/bria/fibo-2/generate", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/bytedance/seedance-2.0/fast/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video at the default resolution 720p, the only per-second rate the page states; fal bills tokens at $0.0112 per 1000 tokens, counts input video duration, and multiplies by 0.6 with video inputs"}, + "mode": "video_generation", + "output_cost_per_second": 0.2419, + "output_cost_per_second_720p": 0.2419, + "source": "https://fal.ai/models/bytedance/seedance-2.0/fast/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/us/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; 1080p and 4k are not priced on the page; fal bills tokens at $0.0168 per 1000 tokens, counts input video duration, and multiplies by 0.6 with video inputs"}, + "mode": "video_generation", + "output_cost_per_second": 0.37, + "output_cost_per_second_480p": 0.1731, + "output_cost_per_second_720p": 0.37, + "source": "https://fal.ai/models/bytedance/seedance-2.0/us/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.5/us/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; with video references fal bills input and output duration and multiplies by 0.6"}, + "mode": "video_generation", + "output_cost_per_second": 0.473, + "output_cost_per_second_1080p": 1.164, + "output_cost_per_second_480p": 0.2205, + "output_cost_per_second_720p": 0.473, + "source": "https://fal.ai/models/bytedance/seedance-2.5/us/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/bria/background/remove": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image without a prompt (prompt is optional); $0.03 per image when a prompt is given has no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.018, + "source": "https://fal.ai/models/fal-ai/bria/background/remove", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/bytedance-upscaler/upscale/video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by target_resolution at 30fps in normal mode; output_cost_per_second is the default target_resolution 1080p rate; 6k $0.0574 and 8k $0.1148 per second have no catalog field; 30-60fps doubles, over 60fps quadruples and pro mode multiplies by 10, none of which is modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.0072, + "output_cost_per_second_1080p": 0.0072, + "output_cost_per_second_2k": 0.0144, + "output_cost_per_second_4k": 0.0288, + "source": "https://fal.ai/models/fal-ai/bytedance-upscaler/upscale/video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/emu-3.5-image/edit-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image at the default 720p resolution; 480p is $0.15 per image and has no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.3, + "source": "https://fal.ai/models/fal-ai/emu-3.5-image/edit-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/emu-3.5-image/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image at the default 720p resolution; 480p is $0.15 per image and has no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.3, + "source": "https://fal.ai/models/fal-ai/emu-3.5-image/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/kling-video/v2.5-turbo/pro/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.07, + "source": "https://fal.ai/models/fal-ai/kling-video/v2.5-turbo/pro/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v2.5-turbo/pro/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.07, + "source": "https://fal.ai/models/fal-ai/kling-video/v2.5-turbo/pro/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/kling-video/v2.5-turbo/standard/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.042, + "source": "https://fal.ai/models/fal-ai/kling-video/v2.5-turbo/standard/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/minimax/hailuo-02/standard/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768P rate; 512P is roughly $0.017 per second and has no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.045, + "output_cost_per_second_768p": 0.045, + "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02/standard/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/minimax/image-01": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://fal.ai/models/fal-ai/minimax/image-01", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/object-removal": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image at the default model best_quality; low_quality $0.006, medium_quality $0.012 and high_quality $0.018 per image have no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.024, + "source": "https://fal.ai/models/fal-ai/object-removal", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/object-removal/bbox": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image at the default model best_quality; low_quality $0.006, medium_quality $0.012 and high_quality $0.018 per image have no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.024, + "source": "https://fal.ai/models/fal-ai/object-removal/bbox", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/object-removal/mask": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image at the default model best_quality; low_quality $0.006, medium_quality $0.012 and high_quality $0.018 per image have no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.024, + "source": "https://fal.ai/models/fal-ai/object-removal/mask", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/recraft/v3/image-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image at the default realistic_image style; vector styles are $0.08 per image and have no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/fal-ai/recraft/v3/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/scail-2": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.2, + "source": "https://fal.ai/models/fal-ai/scail-2", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan-vace-apps/long-reframe": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution, converted from the page rate per 2 seconds ($0.08 per 2s at 720p, $0.04 per 2s at 480p); output_cost_per_second is the 720p rate because the default resolution is auto; 580p ($0.06 per 2s) has no catalog field, 240p and 360p are not priced on the page; seconds are rounded up to a multiple of 2"}, + "mode": "video_generation", + "output_cost_per_second": 0.04, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_720p": 0.04, + "source": "https://fal.ai/models/fal-ai/wan-vace-apps/long-reframe", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-14b/animate/move": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per video second of output by resolution, where a video second is 16 frames; output_cost_per_second is the default resolution 480p rate; 580p is $0.06 per video second and has no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.04, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-14b/animate/move", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/wan/v2.2-14b/animate/replace": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per video second of output by resolution, where a video second is 16 frames; output_cost_per_second is the default resolution 480p rate; 580p is $0.06 per video second and has no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.04, + "output_cost_per_second_480p": 0.04, + "output_cost_per_second_720p": 0.08, + "source": "https://fal.ai/models/fal-ai/wan/v2.2-14b/animate/replace", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.2/edit": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, + "mode": "video_generation", + "output_cost_per_second": 0.0819, + "output_cost_per_second_1080p": 0.1229, + "output_cost_per_second_4k": 0.2457, + "output_cost_per_second_720p": 0.0819, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/edit", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.2/extend": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, + "mode": "video_generation", + "output_cost_per_second": 0.0819, + "output_cost_per_second_1080p": 0.1229, + "output_cost_per_second_4k": 0.2457, + "output_cost_per_second_720p": 0.0819, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/extend", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.2/image-to-video": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, + "mode": "video_generation", + "output_cost_per_second": 0.0819, + "output_cost_per_second_1080p": 0.1229, + "output_cost_per_second_4k": 0.2457, + "output_cost_per_second_720p": 0.0819, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.2/reference-to-video": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, + "mode": "video_generation", + "output_cost_per_second": 0.0819, + "output_cost_per_second_1080p": 0.1229, + "output_cost_per_second_4k": 0.2457, + "output_cost_per_second_720p": 0.0819, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/gemini-omni-flash/v1.2/text-to-video": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, + "mode": "video_generation", + "output_cost_per_second": 0.0819, + "output_cost_per_second_1080p": 0.1229, + "output_cost_per_second_4k": 0.2457, + "output_cost_per_second_720p": 0.0819, + "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/google/virtual-try-on": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.075, + "source": "https://fal.ai/models/google/virtual-try-on", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/ideogram/v4/tiling": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per megapixel at the default rendering_speed BALANCED; TURBO is $0.03 and QUALITY is $0.10 per megapixel, no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.06, + "output_cost_per_pixel": 5.7220458984375e-08, + "source": "https://fal.ai/models/ideogram/v4/tiling", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/ideogram/v4/tiling/lora": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per megapixel at the default rendering_speed BALANCED; TURBO is $0.03375 and QUALITY is $0.1125 per megapixel, no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.0675, + "output_cost_per_pixel": 6.437301635742188e-08, + "source": "https://fal.ai/models/ideogram/v4/tiling/lora", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/kling/v4/flash/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video at 720p (the only resolution) with image references; with video references fal bills $0.063 per second on the output duration plus the greater of the input and output durations, which has no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.094, + "output_cost_per_second_720p": 0.094, + "source": "https://fal.ai/models/kling/v4/flash/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/kling/v4/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution with image references; output_cost_per_second is the default resolution 1080p rate; with video references or video elements fal bills $0.094 (720p) or $0.141 (1080p) per second on the input plus output length, which has no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.235, + "output_cost_per_second_1080p": 0.235, + "output_cost_per_second_720p": 0.157, + "source": "https://fal.ai/models/kling/v4/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/luma/agent/ray/v3.2/reframe": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per started source second by resolution; output_cost_per_second is the default resolution 540p rate ($0.06), which has no tier field"}, + "mode": "video_generation", + "output_cost_per_second": 0.06, + "output_cost_per_second_1080p": 0.36, + "output_cost_per_second_720p": 0.12, + "source": "https://fal.ai/models/luma/agent/ray/v3.2/reframe", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of requested output duration by resolution; output_cost_per_second is the default resolution 768P rate; the page states no promotion for this endpoint; reference tokens above the 4,096 included per request are $0.02 per 1,000 tokens and are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.16, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/styles/16bit-pixel": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/styles/16bit-pixel", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/styles/hand-drawn": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/styles/hand-drawn", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/styles/low-poly": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/styles/low-poly", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/styles/retro-toon-70s": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/styles/retro-toon-70s", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3-max/styles/vhs": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "source": "https://fal.ai/models/minimax/h3-max/styles/vhs", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/mirelo-ai/sfx2.0/video-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated audio per sample; promotional 33% off rate through 2026-12-13 per the page; the standard rate of $0.015 per second applies from 2026-12-14 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10); mode and endpoint follow fal_ai/sonilo/v1.1/video-to-video-sound-effects"}, + "mode": "video_generation", + "output_cost_per_second": 0.01, + "source": "https://fal.ai/models/mirelo-ai/sfx2.0/video-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/nvidia/cosmos-3-super/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per generated image; the optional $0.02 per request prompt expansion surcharge is not modeled, and agentic generation bills every candidate image"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/nvidia/cosmos-3-super/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/recraft/v4/style/pro/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per generated image when a style_id is provided; the one-time $0.005 style creation surcharge when no style_id is given is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.1, + "source": "https://fal.ai/models/recraft/v4/style/pro/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/recraft/v4/style/pro/text-to-vector": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per generated image when a style_id is provided; the one-time $0.005 style creation surcharge when no style_id is given is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.12, + "source": "https://fal.ai/models/recraft/v4/style/pro/text-to-vector", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/recraft/v4/style/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per generated image when a style_id is provided; the one-time $0.005 style creation surcharge when no style_id is given is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://fal.ai/models/recraft/v4/style/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/recraft/v4/style/text-to-vector": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per generated image when a style_id is provided; the one-time $0.005 style creation surcharge when no style_id is given is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://fal.ai/models/recraft/v4/style/text-to-vector", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/vast/eden-live-14b-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of video generated in a live session; the 10 billable second ($0.10) minimum per session is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.01, + "source": "https://fal.ai/models/vast/eden-live-14b-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/vast/eden-live-5b-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of video generated in a live session; the 10 billable second ($0.035) minimum per session is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.0035, + "source": "https://fal.ai/models/vast/eden-live-5b-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-image/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.022, + "source": "https://fal.ai/models/xai/grok-imagine-image/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xai/grok-imagine-video/edit-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the 720p rate because the default resolution is auto; the $0.01 per second of input video charge is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.07, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.07, + "source": "https://fal.ai/models/xai/grok-imagine-video/edit-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-video/extend-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the 720p rate because the endpoint has no resolution field; the $0.01 per second of input video charge is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.07, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.07, + "source": "https://fal.ai/models/xai/grok-imagine-video/extend-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-video/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; the $0.002 per request image input charge is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.07, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.07, + "source": "https://fal.ai/models/xai/grok-imagine-video/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-video/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 480p rate; the $0.002 per request image input charge is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.05, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.07, + "source": "https://fal.ai/models/xai/grok-imagine-video/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-video/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate"}, + "mode": "video_generation", + "output_cost_per_second": 0.07, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.07, + "source": "https://fal.ai/models/xai/grok-imagine-video/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-video/v1.5/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; the $0.01 per reference image charge is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.14, + "output_cost_per_second_1080p": 0.25, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/xai/grok-imagine-video/v1.5/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 480p rate; the $0.01 per reference image charge is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.14, + "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "databricks/databricks-claude-fable-5-2": { + "cache_creation_input_token_cost": 9.99999e-06, + "cache_creation_input_token_cost_above_1hr": 1.599997e-05, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_token": 8.00002e-06, + "input_dbu_cost_per_token": 0.000114286, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "metadata": {"notes":"Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields."}, + "mode": "chat", + "output_cost_per_token": 4.000003e-05, + "output_dbu_cost_per_token": 0.000571429, + "prompt_cache_min_tokens": 512.0, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_anthropic_thinking_payload": true, + "supports_assistant_prefill": false, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": true + }, + "databricks/system.ai.claude-fable-5-2": { + "cache_creation_input_token_cost": 9.99999e-06, + "cache_creation_input_token_cost_above_1hr": 1.599997e-05, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_token": 8.00002e-06, + "input_dbu_cost_per_token": 0.000114286, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "metadata": {"notes":"Claude Fable 5.2 on Databricks is served through Unity Gateway with the model service name system.ai.claude-fable-5-2, hosted through Amazon Bedrock. Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields."}, + "mode": "chat", + "output_cost_per_token": 4.000003e-05, + "output_dbu_cost_per_token": 0.000571429, + "prompt_cache_min_tokens": 512.0, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_anthropic_thinking_payload": true, + "supports_assistant_prefill": false, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": true + }, + "replicate/google/gemini-4-carbon": { + "input_cost_per_token": 2e-06, + "litellm_provider": "replicate", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "mode": "chat", + "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_token": 1e-05, + "source": "https://replicate.com/google/gemini-4-carbon", + "supports_audio_input": true, + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_video_input": true, + "supports_vision": true + }, + "azure_ai/mistral-large-4-latest": { + "deprecation_date": "2027-10-27", + "deprecation_source": "https://management.azure.com/subscriptions/{subscriptionId}/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", + "input_cost_per_token": 7e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.1e-06, + "source": "https://docs.mistral.ai/models/mistral-large-4-0", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fal_ai/fal-ai/recraft-20b": { + "litellm_provider": "fal_ai", + "metadata": {"notes":"per image at the default realistic_image style, from the fal pricing API; vector styles cost 2x and have no catalog field; the fal.ai page for this id redirects to fal-ai/recraft/v2/text-to-image, which rounds the rate to $0.022"}, + "mode": "image_generation", + "output_cost_per_image": 0.0219, + "source": "https://api.fal.ai/v1/models/pricing?endpoint_id=fal-ai/recraft-20b", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/stable-diffusion-v3-medium/image-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.035, + "source": "https://api.fal.ai/v1/models/pricing?endpoint_id=fal-ai/stable-diffusion-v3-medium/image-to-image", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/pixverse/lipsync": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of output video; when audio_url is not provided the text is spoken with TTS at $0.24 per 100 characters, which is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.04, + "source": "https://fal.ai/models/fal-ai/pixverse/lipsync", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "bedrock_mantle/us-gov-east-1/openai.gpt-5.6-cyber": { + "cache_creation_input_token_cost": 2.109375e-05, + "cache_read_input_token_cost": 1.6875e-06, + "input_cost_per_token": 1.6875e-05, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.00010125, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-cyber.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false, + "supports_xhigh_reasoning_effort": true, + "use_openai_responses_path": true + }, + "fal_ai/fal-ai/kling-video/v2.6/pro/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video with the default generate_audio=true ($0.14); videos without audio are $0.07 per second and videos with audio and voice control are $0.168 per second, which have no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.14, + "source": "https://fal.ai/models/fal-ai/kling-video/v2.6/pro/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/vidu/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second derived from the fixed 4s clip price of $0.20 per video"}, + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/fal-ai/vidu/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/vidu/start-end-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second derived from the fixed 4s clip price of $0.20 per video"}, + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/fal-ai/vidu/start-end-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/vidu/reference-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second derived from the fixed 4s clip price of $0.40 per video"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://fal.ai/models/fal-ai/vidu/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/luma/agent/ray/v3.2/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second derived from the 5s clip prices by resolution ($0.15 at 540p, $0.30 at 720p, $1.20 at 1080p); output_cost_per_second is the default resolution 540p rate, which has no tier field; HDR ($0.60 at 720p, $2.40 at 1080p per 5s) and HDR+EXR ($0.90, $3.60) are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_1080p": 0.24, + "output_cost_per_second_720p": 0.06, + "source": "https://fal.ai/models/luma/agent/ray/v3.2/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/luma/agent/ray/v3.2/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second derived from the 5s and 10s clip prices by resolution ($0.50/$1.00 at 540p, $1.00/$2.00 at 720p, $2.00/$4.00 at 1080p); output_cost_per_second is the default resolution 540p rate, which has no tier field"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.4, + "output_cost_per_second_720p": 0.2, + "source": "https://fal.ai/models/luma/agent/ray/v3.2/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/luma/agent/ray/v3.2/video-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second derived from the 5s and 10s clip prices by resolution ($0.72/$1.44 at 540p, $1.08/$2.16 at 720p, $2.16/$4.32 at 1080p); output_cost_per_second is the default resolution 540p rate, which has no tier field; HDR and HDR+EXR prices are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.144, + "output_cost_per_second_1080p": 0.432, + "output_cost_per_second_720p": 0.216, + "source": "https://fal.ai/models/luma/agent/ray/v3.2/video-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/pixverse/v6/max/text-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution without audio (the default generate_audio_switch=false); output_cost_per_second is the default resolution 720p rate; 360p $0.054 and 540p $0.081 have no catalog field; with audio the rates are $0.081/$0.099/$0.135/$0.252 per second, which is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.099, + "output_cost_per_second_1080p": 0.198, + "output_cost_per_second_720p": 0.099, + "source": "https://fal.ai/models/pixverse/v6/max/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/pixverse/v6/max/image-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second of generated video by resolution without audio (the default generate_audio_switch=false); output_cost_per_second is the default resolution 720p rate; 360p $0.054 and 540p $0.081 have no catalog field; with audio the rates are $0.081/$0.099/$0.135/$0.252 per second, which is not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.099, + "output_cost_per_second_1080p": 0.198, + "output_cost_per_second_720p": 0.099, + "source": "https://fal.ai/models/pixverse/v6/max/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/fal-ai/flux-2-pro": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.03 for the first output megapixel plus $0.015 per additional input or output megapixel, rounded up, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/flux-2-pro", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-pro/edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.03 for the first output megapixel plus $0.015 per additional input or output megapixel, rounded up, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/flux-2-pro/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2-pro/outpaint": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.03 for the first output megapixel plus $0.015 per additional input or output megapixel, rounded up, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/flux-2-pro/outpaint", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-2-max": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.07 for the first processed megapixel plus $0.03 per additional megapixel, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.07, + "source": "https://fal.ai/models/fal-ai/flux-2-max", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/flux-2-max/edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.07 for the first processed megapixel plus $0.03 per additional megapixel, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.07, + "source": "https://fal.ai/models/fal-ai/flux-2-max/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/v1/erase": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per image for the first generated megapixel; fal bills $0.004 for each subsequent generated megapixel and $0.004 per reference megapixel with a 3 MP minimum, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.03, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1/erase", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/smart-resize": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per single-image request at standard resolution: $0.15 per output image plus the $0.05 minimum vision analysis fee per request; additional output images in one request ($0.15 each) and 4K outputs (charged double) are not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.2, + "source": "https://fal.ai/models/fal-ai/smart-resize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bytedance/seedream/v5/pro/layerize": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per generated layer for total pixel area under 1536x1536; layers for a base image over 1536x1536 are $0.0675 each, which has no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.03375, + "source": "https://fal.ai/models/bytedance/seedream/v5/pro/layerize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/luma/agent/uni-1/v1/edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per edit with one source image ($0.042 per edit plus $0.003 per reference or source image); each additional reference image adds $0.003, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.045, + "source": "https://fal.ai/models/luma/agent/uni-1/v1/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/luma/agent/uni-1/v1/max/edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per edit with one source image ($0.102 per edit plus $0.003 per reference or source image); each additional reference image adds $0.003, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.105, + "source": "https://fal.ai/models/luma/agent/uni-1/v1/max/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "databricks/databricks-gemini-4-carbon": { + "cache_creation_input_token_cost": 2e-06, + "cache_read_input_token_cost": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "metadata": {"notes":"Gemini 4 Carbon on Databricks is available only through Unity Gateway with the model service name system.ai.gemini-4-carbon on a global endpoint. The Databricks pricing pages list no row for it yet, so input and output are the Global rates on the Vertex AI pricing page for Gemini 4 Carbon (listed there through November 30, 2026), no '*_dbu_cost_per_token' fields are published, and cache tokens bill at the input rate until Databricks publishes cache DBU rates."}, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "databricks/system.ai.gemini-4-carbon": { + "cache_creation_input_token_cost": 2e-06, + "cache_read_input_token_cost": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "metadata": {"notes":"Gemini 4 Carbon on Databricks is available only through Unity Gateway with the model service name system.ai.gemini-4-carbon on a global endpoint. The Databricks pricing pages list no row for it yet, so input and output are the Global rates on the Vertex AI pricing page for Gemini 4 Carbon (listed there through November 30, 2026), no '*_dbu_cost_per_token' fields are published, and cache tokens bill at the input rate until Databricks publishes cache DBU rates."}, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "runwayml/kling2.5_turbo_pro": { + "litellm_provider": "runwayml", + "metadata": {"comment":"12 credits per second @ $0.01 per credit = $0.12 per second"}, + "mode": "video_generation", + "output_cost_per_second": 0.12, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/kling3.0_standard": { + "litellm_provider": "runwayml", + "metadata": {"comment":"13 credits per second with audio, 9 without @ $0.01 per credit; priced at the with-audio rate (audio defaults to true)"}, + "mode": "video_generation", + "output_cost_per_second": 0.13, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/kling3.0_pro": { + "litellm_provider": "runwayml", + "metadata": {"comment":"17 credits per second with audio, 12 without @ $0.01 per credit; priced at the with-audio rate (audio defaults to true)"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/kling3.0_4k": { + "litellm_provider": "runwayml", + "metadata": {"comment":"43 credits per second @ $0.01 per credit = $0.43 per second, with or without audio"}, + "mode": "video_generation", + "output_cost_per_second": 0.43, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/klingO3_standard": { + "litellm_provider": "runwayml", + "metadata": {"comment":"13 credits per second @ $0.01 per credit = $0.13 per second; video-to-video is billed per second of the input video, not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.13, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/klingO3_pro": { + "litellm_provider": "runwayml", + "metadata": {"comment":"17 credits per second @ $0.01 per credit = $0.17 per second; video-to-video is billed per second of the input video, not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.17, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/klingO3_4k": { + "litellm_provider": "runwayml", + "metadata": {"comment":"43 credits per second @ $0.01 per credit = $0.43 per second; video-to-video is billed per second of the input video, not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.43, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/kling_4_flash": { + "litellm_provider": "runwayml", + "metadata": {"comment":"9.4 credits per second (720p) without input video @ $0.01 per credit = $0.094 per second; the with-input-video rate (6.3 credits per output second plus 6.3 per second of the greater of input and output duration), rounding up to the next credit and the 29 credit minimum are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.094, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/wan3": { + "litellm_provider": "runwayml", + "metadata": {"comment":"5/10/20 credits per second at 480p/720p/1080p @ $0.01 per credit"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.2, + "output_cost_per_second_480p": 0.05, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "runwayml/wan3_prime": { + "litellm_provider": "runwayml", + "metadata": {"comment":"6.8/14/28 credits per second at 480p/720p/1080p @ $0.01 per credit"}, + "mode": "video_generation", + "output_cost_per_second": 0.14, + "output_cost_per_second_1080p": 0.28, + "output_cost_per_second_480p": 0.068, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] }, - "vertex_ai/claude-haiku-5-5@default": { - "input_cost_per_token_above_100k_tokens": 5e-07, - "output_cost_per_token_above_100k_tokens": 2.5e-06, - "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, - "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, - "cache_read_input_token_cost_above_100k_tokens": 5e-08, - "regional_endpoint_uplift_multiplier": 1.1, - "supports_mid_conversation_system": true, - "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_above_1hr": 2e-07, - "cache_creation_input_token_cost_batches": 6.25e-08, - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_batches": 5e-09, - "input_cost_per_token": 1e-07, - "input_cost_per_token_batches": 5e-08, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_batches": 2.5e-07, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_adaptive_thinking": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true, - "supports_forced_tool_use": true, - "thinking_always_on": false, - "prompt_cache_min_tokens": 512, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + "runwayml/grok_imagine_1_5": { + "litellm_provider": "runwayml", + "metadata": {"comment":"10/16/29 credits per second at 480p/720p/1080p @ $0.01 per credit; 1 credit per image or audio reference not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.16, + "output_cost_per_second_1080p": 0.29, + "output_cost_per_second_480p": 0.1, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] }, - "microsoft_365_copilot/chat": { - "litellm_provider": "microsoft_365_copilot", - "mode": "chat", - "supports_mid_conversation_system": true, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0 + "runwayml/grok_imagine_1_5_lite": { + "litellm_provider": "runwayml", + "metadata": {"comment":"2/3/14 credits per second at 480p/720p/1080p @ $0.01 per credit; 1 credit for an image-to-video start frame not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.03, + "output_cost_per_second_1080p": 0.14, + "output_cost_per_second_480p": 0.02, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] }, - "us.twelvelabs.pegasus-1-5-v1:0": { - "input_cost_per_video_per_second": 0.00049, - "litellm_provider": "bedrock", - "max_output_tokens": 98304, - "max_tokens": 98304, - "mode": "chat", - "output_cost_per_token": 7.5e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", - "supports_video_input": true + "runwayml/h3_max": { + "litellm_provider": "runwayml", + "metadata": {"comment":"8 credits per second at 768p, 5 at 480p @ $0.01 per credit"}, + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.05, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] }, - "global.twelvelabs.pegasus-1-5-v1:0": { - "input_cost_per_video_per_second": 0.00049, - "litellm_provider": "bedrock", - "max_output_tokens": 98304, - "max_tokens": 98304, - "mode": "chat", - "output_cost_per_token": 7.5e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", - "supports_video_input": true + "runwayml/happyhorse_1_0": { + "litellm_provider": "runwayml", + "metadata": {"comment":"15 credits per second at 720p, 30 at 1080p @ $0.01 per credit"}, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "output_cost_per_second_1080p": 0.3, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] }, - "twelvelabs.pegasus-1-5-v1:0": { - "input_cost_per_video_per_second": 0.00049, - "litellm_provider": "bedrock", - "max_output_tokens": 98304, - "max_tokens": 98304, - "mode": "chat", - "output_cost_per_token": 7.5e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", - "supports_video_input": true + "runwayml/gemini_omni_flash_1.2": { + "litellm_provider": "runwayml", + "metadata": {"comment":"7/10/21 credits per second at 720p/1080p/4K @ $0.01 per credit; the 360p rate (2 credits per second), 1 credit per reference image or keyframe, 1 credit per second of input video and the 6 credit minimum per request are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.07, + "output_cost_per_second_1080p": 0.1, + "output_cost_per_second_4k": 0.21, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ] }, - "azure_ai/Microsoft-Decision-1": { - "input_cost_per_token": 4.2e-08, - "litellm_provider": "azure_ai", - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=productName eq 'Microsoft Decision Models'" + "runwayml/gemini_omni_flash_1.1": { + "litellm_provider": "runwayml", + "metadata": {"comment":"10/15/30 credits per second at 720p/1080p/4K @ $0.01 per credit; the 360p rate (3.4 credits per second), 1 credit per reference image and 1 credit per second of input video are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "output_cost_per_second_4k": 0.3, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ] }, - "gpt-rosalind-discovery": { - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openai", - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://developers.openai.com/api/docs/pricing" + "runwayml/muse_image": { + "litellm_provider": "runwayml", + "metadata": {"comment":"1 credit per image (any resolution) @ $0.01 per credit = $0.01 per image"}, + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] }, - "chatgpt/gpt-rosalind-discovery": { - "litellm_provider": "chatgpt", - "mode": "responses", - "source": "https://developers.openai.com/api/docs/pricing", - "supported_endpoints": [ - "/v1/responses" + "runwayml/seedream5_lite": { + "litellm_provider": "runwayml", + "metadata": {"comment":"4 credits per image (any resolution) @ $0.01 per credit = $0.04 per image"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" ] }, - "azure_ai/Cohere-Embed-V5-Fast": { - "deprecation_date": "2027-01-23", - "input_cost_per_image_token": 4e-07, - "input_cost_per_token": 8e-08, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_tokens": 128000, - "mode": "embedding", - "output_cost_per_token": 0.0, - "output_vector_size": 2048.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/embeddings" + "runwayml/seedream5_flash": { + "litellm_provider": "runwayml", + "metadata": {"comment":"2 credits per image (any resolution) @ $0.01 per credit = $0.02 per image"}, + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" ], + "supported_output_modalities": [ + "image" + ] + }, + "runwayml/gemini_image3.1_flash_lite": { + "litellm_provider": "runwayml", + "metadata": {"comment":"4 credits per 1K image @ $0.01 per credit = $0.04 per image"}, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], - "supports_embedding_image_input": true + "supported_output_modalities": [ + "image" + ] }, - "azure_ai/Cohere-Embed-V5-Pro": { - "deprecation_date": "2027-01-23", - "input_cost_per_image_token": 4e-07, - "input_cost_per_token": 1.2e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_tokens": 128000, - "mode": "embedding", - "output_cost_per_token": 0.0, - "output_vector_size": 2048.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supported_endpoints": [ - "/v1/embeddings" + "runwayml/bria_fibo_edit_1_5": { + "litellm_provider": "runwayml", + "metadata": {"comment":"5 credits per image @ $0.01 per credit = $0.05 per image"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" ], + "supported_output_modalities": [ + "image" + ] + }, + "runwayml/gemini_2.5_flash": { + "litellm_provider": "runwayml", + "metadata": {"comment":"5 credits per image (any resolution) @ $0.01 per credit = $0.05 per image"}, + "mode": "image_generation", + "output_cost_per_image": 0.05, + "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], - "supports_embedding_image_input": true + "supported_output_modalities": [ + "image" + ] }, - "scaledown/extract": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "scaledown", - "mode": "chat", - "supports_response_schema": false, - "supports_system_messages": false, - "supports_vision": false, - "supports_function_calling": false + "runwayml/eleven_v3": { + "input_cost_per_character": 0.0002, + "litellm_provider": "runwayml", + "metadata": {"comment":"1 credit per 50 characters @ $0.01 per credit = $0.0002 per character; 1 credit minimum not modeled"}, + "mode": "audio_speech", + "source": "https://docs.dev.runwayml.com/guides/pricing/" }, - "scaledown/summarize": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "scaledown", - "mode": "chat", - "supports_system_messages": true, - "supports_vision": false, - "supports_function_calling": false + "runwayml/eleven_v4": { + "input_cost_per_character": 5e-05, + "litellm_provider": "runwayml", + "metadata": {"comment":"5 credits per 1,000 characters @ $0.01 per credit = $0.00005 per character; 1 credit minimum not modeled"}, + "mode": "audio_speech", + "source": "https://docs.dev.runwayml.com/guides/pricing/" }, - "scaledown/compress": { - "input_cost_per_token": 5e-08, + "gemini/gemini-decision-1": { + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "max_input_tokens": 262144, + "mode": "decisions", "output_cost_per_token": 0.0, - "litellm_provider": "scaledown", - "mode": "chat", - "supports_system_messages": true, + "rpm": 1500, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/decisions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_computer_use": false, "supports_function_calling": false, - "supports_vision": false + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_url_context": false, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": false, + "tpm": 1000000 }, - "scaledown/classify": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "scaledown", - "mode": "chat", - "supports_system_messages": false, - "supports_vision": false, - "supports_function_calling": false + "runwayml/kling_4": { + "litellm_provider": "runwayml", + "metadata": {"comment":"Promo rate through 2026-11-30 UTC: 12.56 credits per second (720p) and 18.8 (1080p) without input video @ $0.01 per credit = $0.1256 and $0.188 per second; list rate 15.7/23.5 credits per second applies from 2026-12-01 UTC (ruling runwayml-kling-4-promo-rate). The with-input-video rate (7.52/11.28 credits per output second plus the same per second of the greater of input and output duration) and rounding up to the next credit are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.1256, + "output_cost_per_second_1080p": 0.188, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ] }, - "scaledown/decisions": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "scaledown", - "mode": "chat", - "supports_system_messages": false, - "supports_vision": false, - "supports_function_calling": false + "fal_ai/bytedance/seedream/v5.5/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per image at the default image_size auto_2K; 1K and 1.5K outputs are $0.03 and custom dimensions are $0.03 up to and including 2,610,000 pixels and $0.0405 above, so 1.5K has no catalog field"}, + "mode": "image_generation", + "output_cost_per_image": 0.0405, + "output_cost_per_image_1K": 0.03, + "output_cost_per_image_2K": 0.0405, + "source": "https://fal.ai/models/bytedance/seedream/v5.5/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "vertex_ai/gemini-robotics-er-2-preview": { - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_batches": 5e-08, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1e-06, - "input_cost_per_token_batches": 5e-07, - "litellm_provider": "vertex_ai", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, + "fal_ai/bytedance/seedream/v5.5/edit": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per output image with one input image at the default image_size auto_2K ($0.0405 per output plus $0.012 per input image per output); 1K and 1.5K outputs are $0.03 plus the input fee and each additional input image adds $0.012 per output, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.0525, + "output_cost_per_image_1K": 0.042, + "output_cost_per_image_2K": 0.0525, + "source": "https://fal.ai/models/bytedance/seedream/v5.5/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/bytedance/seedream/v5.5/layerize": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per returned output image (the base image and every separated layer) at the default image_size auto, where a base image above 2,610,000 pixels bills $0.0405 per output and one at or under that area bills $0.03; fal also bills $0.012 for the input image once per request and returns up to max_images (default 30) outputs, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.0405, + "output_cost_per_image_1K": 0.03, + "output_cost_per_image_2K": 0.0405, + "source": "https://fal.ai/models/bytedance/seedream/v5.5/layerize", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux-pro/v1/vto": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per try-on with one 1 MP input image and one 1 MP output ($0.0375 for the first input megapixel plus $0.005 per output megapixel); fal bills $0.005 per additional input megapixel and rounds each input image and the output up to whole megapixels separately, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.0425, + "source": "https://fal.ai/models/fal-ai/flux-pro/v1/vto", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/patina/material": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per request at the schema defaults (1024x1024 square_hd, all 5 maps, no upscaling), the page's own example; fal bills $0.01 per request plus $0.02 per megapixel plus $0.01 per megapixel per map type, and 2x or 4x upscaling adds $0.004 or $0.016 per pre-upscaling megapixel per map, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.08, + "source": "https://fal.ai/models/fal-ai/patina/material", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/patina/material/extract": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per request at the schema defaults (1024x1024 input, all 5 maps, no upscaling), the page's own example; fal bills $0.10 per request plus $0.02 per megapixel plus $0.01 per megapixel per map type, and 2x or 4x upscaling adds $0.004 or $0.016 per pre-upscaling megapixel per map, which is not modeled"}, + "mode": "image_generation", + "output_cost_per_image": 0.17, + "source": "https://fal.ai/models/fal-ai/patina/material/extract", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/vidu/template-to-video": { + "litellm_provider": "fal_ai", + "metadata": {"comment":"per second derived from the $0.20 Standard template price over the fixed 4s clip the sibling vidu endpoints state; Premium templates are $0.30 and Advanced templates $0.50 per video, which has no catalog field"}, + "mode": "video_generation", + "output_cost_per_second": 0.05, + "source": "https://fal.ai/models/fal-ai/vidu/template-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "gemini/gemini-4-hydrogen": { + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_flex": 7.5e-07, + "input_cost_per_token_priority": 2.7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_reasoning_token": 5e-06, - "output_cost_per_token": 5e-06, - "output_cost_per_token_batches": 2.5e-06, + "output_cost_per_reasoning_token": 7.5e-06, + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, + "output_cost_per_token_flex": 3.75e-06, + "output_cost_per_token_priority": 1.35e-05, + "prompt_cache_min_tokens": 4096.0, + "rpm": 2000.0, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, + "source": "https://aistudio.google.com/docs/pricing#gemini-4-hydrogen", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/completions" ], "supported_modalities": [ "text", @@ -72476,7 +101094,11 @@ ], "supports_audio_input": true, "supports_audio_output": false, + "supports_computer_use": true, + "supports_continuation": true, "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -72488,24 +101110,36 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, + "tpm": 800000.0, "web_search_billing_unit": "per_query" }, - "gemini-robotics-er-2-preview": { - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_batches": 5e-08, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1e-06, - "input_cost_per_token_batches": 5e-07, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, + "vertex_ai/gemini-4-hydrogen": { + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token": 1.5e-06, + "input_cost_per_audio_token_batches": 7.5e-07, + "input_cost_per_audio_token_priority": 2.7e-06, + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_flex": 7.5e-07, + "input_cost_per_token_priority": 2.7e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", - "output_cost_per_reasoning_token": 5e-06, - "output_cost_per_token": 5e-06, - "output_cost_per_token_batches": 2.5e-06, - "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "output_cost_per_reasoning_token": 7.5e-06, + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, + "output_cost_per_token_flex": 3.75e-06, + "output_cost_per_token_priority": 1.35e-05, + "prompt_cache_min_tokens": 4096.0, + "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, + "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -72522,7 +101156,11 @@ ], "supports_audio_input": true, "supports_audio_output": false, + "supports_computer_use": true, + "supports_continuation": true, "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true,