llm-api-pricing

Claude Opus 5 API (claude-opus-5): model id, per-million-token pricing, cache write and cache read rates, streaming and Anthropic-style requests through an OpenAI-compatible gateway.

AI API pricing comparison: per-image, per-second and per-million-token costs for image2.5, Nano Banana 2/Pro, Grok Image, Seedance, GPT-5.5, Claude Opus 5 and DeepSeek, refreshed daily from the public pricing payload.

DeepSeek 4 API (deepseek-v4-flash / deepseek-v4-pro): model ids, per-million-token pricing, cached-input rates, context limits and OpenAI-compatible API examples.

GPT-5.5 API (gpt-5.5 / gpt-5.5-pro): model ids, per-million-token pricing, context limits, streaming, tool calling and OpenAI-compatible base URL examples.

DeepSeek 4 API pricing: per-million-token input, cached input and output rates for deepseek-v4-pro and deepseek-v4-flash with worked cost examples for real workloads.

glm-5.3-flash API (glm5.3flash / glm 5.3 flash): input $0.06; cached_input $0.012; output $0.2. Model id, llm settings, curl and Python examples over an OpenAI-compatible gateway,

claude-opus-4.7 API (claudeopus4.7 / claude opus 4.7): input $4; cached_input $0.4; cache_write_5m $5. Model id, llm-pricing settings, curl and Python examples over an OpenAI-compa

gemini-3-pro API (gemini3pro / gemini 3 pro): input $1.6; output $9.6. Model id, llm settings, curl and Python examples over an OpenAI-compatible gateway, $1 minimum top-up.

claude-sonnet-5 API (claudesonnet5 / claude sonnet 5): input $1.6; cached_input $0.16; cache_write_5m $2. Model id, llm settings, curl and Python examples over an OpenAI-compatible

gpt-5.6-luna API (gpt5.6luna / gpt 5.6 luna): input $0.16; cached_input $0.016; cache_write $0.2. Model id, llm settings, curl and Python examples over an OpenAI-compatible gateway

deepseek-v4-pro API (deepseekv4pro / deepseek v4 pro): input $1.0286; cached_input $0.2057; output $3.0857. Model id, llm settings, curl and Python examples over an OpenAI-compatib

gpt-5.6-terra API (gpt5.6terra / gpt 5.6 terra): input $1.6; cached_input $0.16; cache_write $2. Model id, llm settings, curl and Python examples over an OpenAI-compatible gateway,

midjourney API (midjourney / midjourney): default $0.045; imagine $0.045; imagine-niji6 $0.045. Model id, gateway settings, curl and Python examples over an OpenAI-compatible gatew

veo-3.1 API (veo3.1 / veo 3.1): default $0.07; extend $0.07; 4K $0.57. Model id, gateway settings, curl and Python examples over an OpenAI-compatible gateway, $1 minimum top-up.

grok-4.5 API (grok4.5 / grok 4.5): input $1.6; output $3.2. Model id, llm settings, curl and Python examples over an OpenAI-compatible gateway, $1 minimum top-up.

midjourney API (midjourney / midjourney): default $0.045; imagine $0.045; imagine-niji6 $0.045. Model id, prompts settings, curl and Python examples over an OpenAI-compatible gatew

qwen3.8-flash API (qwen3.8flash / qwen3.8 flash): input $0.0914; cached_input $0.0114; explicit_cached_input $0.0114. Model id, llm settings, curl and Python examples over an OpenA

gpt-6-astra API (gpt6astra / gpt 6 astra): input $8; cached_input $0.8; cache_write $10. Model id, llm-pricing settings, curl and Python examples over an OpenAI-compatible gateway,

qwen3.7-flash API (qwen3.7flash / qwen3.7 flash): input $0.0229; cached_input $0.0046; explicit_cached_input $0.0023. Model id, llm settings, curl and Python examples over an OpenA

grok-4.5 API (grok4.5 / grok 4.5): input $1.6; output $3.2. Model id, llm-pricing settings, curl and Python examples over an OpenAI-compatible gateway, $1 minimum top-up.