chore: sync new models - #1227
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: 8486140c43
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".
| "input_cost_per_mil_tokens": 5, | ||
| "input_cache_read_cost_per_mil_tokens": 1.25, |
There was a problem hiding this comment.
When any of the four new GPT-Image 2.5 aliases returns billed output tokens, these entries expose input and cache-read pricing but no output_cost_per_mil_tokens, so catalog consumers cannot include output usage and will underreport the request cost. The existing gpt-image-2 entries at lines 1864-1883 carry the otherwise identical $5 input/$1.25 cache pricing together with a $10 output rate; populate the verified output rate for both 2.5 variants and their dated snapshots as well.
Useful? React with 👍 / 👎.
1 participant
Automated sync of model metadata and newly available models from the approved provider allowlist.