[scx-ai] Add SCX.ai pricing and model configs - #874
Open
bhuvan2134686 wants to merge 4 commits into
Open
Conversation
bhuvan2134686
force-pushed
the
provider/scx-ai
branch
from
August 6, 2026 02:03
c6f1e79 to
f3fdea6
Compare
bhuvan2134686
changed the title
bhuvan2134686
force-pushed
the
provider/scx-ai
branch
from
August 6, 2026 02:08
f3fdea6 to
e944d7d
Compare
bhuvan2134686
changed the title
SCX.ai is an Australian AI platform with an OpenAI-compatible API at https://api.scx.ai/v1. Adds pricing and general configs for GLM-5.2 and qwen3.8-max. Prices are cents per token (USD/M / 10,000): GLM-5.2 $0.822/M in, $0.206/M cached, $2.888/M out qwen3.8-max $1.815/M in, $0.21/M cached, $5.4461/M out Both carry a 131072 max_tokens ceiling. For GLM-5.2 this comes from the endpoint's own validator rather than the published catalogue, which advertises a stale 4096.
bhuvan2134686
force-pushed
the
provider/scx-ai
branch
from
August 6, 2026 02:31
e944d7d to
348fc67
Compare
Add pricing and configs for the six models SCX.ai now serves publicly: GLM-5.2-Fast, MiniMax-M2.7, gpt-oss-120b, gemma-4-31B-it, Qwen3-32B and Llama-4-Maverick-17B-128E-Instruct. Update GLM-5.2 to SCX's current (reduced) rates. max_tokens ceilings come from the endpoint's own validators, probed live on 2026-08-27 (accept/reject boundary per model). qwen3.8-max is now serving on the public API and image input was verified live, so 'image' is added to its supported types.
Author
|
Updated to SCX's current catalogue and rates: GLM-5.2-Fast added, GLM-5.2 and qwen3.8-max synced to SCX's official pricing page (https://scx.ai/pricing, which now publishes per-token USD rates with per-model detail pages), and |
Drop MiniMax-M2.7, gpt-oss-120b, gemma-4-31B-it, Qwen3-32B and Llama-4-Maverick-17B-128E-Instruct — SCX is limiting this listing to its three headline models.
SCX now publishes first-party per-token USD rates at https://scx.ai/pricing (with per-model pages). Align both models to the currently billed prices: GLM-5.2 at 0.61/0.22/1.98 USD per million (in/cached/out) and qwen3.8-max at 1.65/0.21/4.99. GLM-5.2-Fast already matches its published page.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds pricing and model configs for SCX.ai, an Australian AI platform serving models over an OpenAI-compatible API (
https://api.scx.ai/v1).Companion gateway PR: Portkey-AI/gateway#1760
Files
pricing/scx-ai.json— pay-as-you-go ratesgeneral/scx-ai.json— params,max_tokensceilings and capability flagsPricing
Prices are cents per token (
USD per million ÷ 10,000):GLM-5.2GLM-5.2-Fastqwen3.8-maxSource: SCX's official pricing page, https://scx.ai/pricing, which publishes per-token USD rates with a per-model detail page for each entry (GLM-5.2, GLM-5.2-Turbo, Qwen3.8-Max).
Note: the website currently titles the fast variant "GLM-5.2-Turbo", but the API serves it as
GLM-5.2-Fast(verified live —GLM-5.2-Turboreturns "Unsupported model"), so that is the key used here.Model configs
All three models are chat with tool calling;
qwen3.8-maxadditionally accepts image input (verified live — an image round-trip returned the correct answer and billedimage_tokens).max_tokensceilings come from each endpoint's own validator rather than the/v1/modelscatalogue (which advertises a stale4096), probed live on 2026-08-27:max_tokensceilingGLM-5.2GLM-5.2-Fastqwen3.8-maxValidation
jq emptypasses on both filespython3 scripts/check_duplicate_keys.py→ no duplicate keysprettier@2.8.8 --checkpasses