chore: sync new models - #1292
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
![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: 054f56d1b8
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".
| "reasoning": true, | ||
| "max_input_tokens": 131072, | ||
| "max_output_tokens": 65536, | ||
| "max_input_tokens": 128072, |
There was a problem hiding this comment.
Correct the new 128072 value to 131072. GPT-OSS 120B has a 131,072-token context window, as reflected by this entry before the change and by the other provider-specific GPT-OSS entries in the catalog; the transposed value understates the model's capacity by 3,000 tokens for every client that consumes this metadata.
Useful? React with 👍 / 👎.
This branch was successfully deployed
1 participant
Automated sync of model metadata and newly available models from the approved provider allowlist.