fix(pricing): update OpenAI model rates and accounting - #10
Conversation
Add current GPT, Codex, and o-series prices, long-context tiers, cache-write accounting, aliases, and regression coverage.\n\nCo-Authored-By: Claude <noreply@anthropic.com>
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
馃挕 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 112e21bb75
鈩癸笍 About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 馃憤.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| "o1-2024-12-17": "openai/o1", | ||
| "o1-mini-2024-09-12": "openai/o1-mini", |
There was a problem hiding this comment.
Add exact aliases for o1-preview and o1-preview-2024-09-12 when replacing the old contains("o1") fallback. Historical logs containing either official model ID now fall through to the generic $3/$15 estimate instead of the o1 rate, and provider(forCanonicalKey:) consequently labels them as Claude rather than Codex, corrupting both historical spend and model/provider attribution.
Useful? React with 馃憤聽/ 馃憥.
1 participant
Summary
Verification
swift buildmake testCODINGBAR_VERSION=v1.1.9 make packagecodesign --verify --deep --strictand--self-test馃 Generated with Claude Code