chore: update model catalog from bot issues - #1003
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Codex (@codex) review |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 6b2a6ec3d4
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "Codex (@codex) review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "Codex (@codex) address that feedback".
| "databricks-meta-llama-3-1-8b-instruct": ["databricks"], | ||
| "openai/gpt-oss-120b": ["groq", "together", "baseten"], | ||
| "openai/gpt-oss-20b": ["groq"], // NOTE: We use groq pricing for this and Together pricing for the 120B model | ||
| "openai/gpt-oss-20b": ["groq", "together"], |
There was a problem hiding this comment.
This makes openai/gpt-oss-20b routable through Groq while the same commit changes the catalog price to Together's lower $0.05/$0.20 rate; Groq's current public price for GPT OSS 20B is still $0.075/$0.30 (Groq, Together). The proxy chooses among returned provider secrets starting at a random index (packages/proxy/src/proxy.ts:1422-1439), and the billing callback sends only model/token counts, not the chosen provider (packages/proxy/src/proxy.ts:1235-1246), so any request that lands on a Groq secret for this model will be costed from the Together-priced catalog entry. Keep this id pinned to one priced provider, or keep Groq pricing while Groq remains routable.
Useful? React with 👍 / 👎.
Single catalog PR containing every genuine "update model catalog" change from the week (#989/#1000/#1003/#1008/#1014/#1017/#1021/#1024), rebuilt on current main after #1009 (sync) and #986 (deprecation) merged. 28 new models + 22 metadata/deprecation-marking changes, with prior review fixes: gemma-3 converse format, gpt-5.6 bedrock cache-write, databricks-glm-5-2 1M context, vertex llama-4 maas pricing/quota, gpt-oss-20b groq-only pin, proxy.ts OpenAI/xAI vertex-maas OpenAPI routing. Also restores GLM-5.2 cached-input to $0.26 (Baseten/Together) — the merged sync left main at Fireworks' $0.14. Validated: gemma-3-4b/12b + nemotron + GLM-5.2 invoke 200 via gateway. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
1 participant
Automated daily batch of model catalog updates from bot issues.
Included issues
Summary
openai/gpt-oss-20bopenai/gpt-oss-20b2
3
Verified metadata
#1001: [BOT ISSUE] Together: stale pricing for openai/gpt-oss-20b ($0.075/$0.30 → $0.05/$0.20)
Verification notes
No LLM verification step ran; model metadata was already complete in the issue.
sync_models vs proposed update
sync_models cross-check found differences. Official provider verification was used for the applied values, and sync_models discrepancies are listed below for review.