release: 2.51.0 - #3553
Conversation
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 0cb7e0ddbe
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 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 address that feedback".
| safety_identifier: Optional[str] | Omit = omit, | ||
| seed: Optional[int] | Omit = omit, | ||
| service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit, | ||
| service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit, |
There was a problem hiding this comment.
Propagate fast tier to chat helper signatures
The new literal is only added to the generated create() surfaces, but the chat helper APIs still expose the old enum (parse() at line 118, stream() at line 1574, and async equivalents at lines 1729/3185) while forwarding service_tier through to create(). In typed code, client.chat.completions.parse(..., service_tier="fast") or .stream(..., service_tier="fast") is still rejected even though this change documents Fast mode support for Chat Completions.
Useful? React with 👍 / 👎.
| reasoning: Optional[Reasoning] | Omit = omit, | ||
| safety_identifier: Optional[str] | Omit = omit, | ||
| service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit, | ||
| service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit, |
There was a problem hiding this comment.
Propagate fast tier to responses helpers
The standard responses.create() overloads now accept service_tier="fast", but the Responses helper signatures still use the old literal set (stream() overload/implementation at lines 1108/1151 and parse() at line 1313, plus async at lines 2943/2986/3147). Typed users who opt in via client.responses.stream(..., service_tier="fast") or .parse(...) still get an invalid-literal error even though these helpers send the same request parameter.
Useful? React with 👍 / 👎.
0cb7e0d to
fa66352
Compare
|
🤖 Release is at https://github.com/openai/openai-python/releases/tag/v2.51.0 🌻 |
Automated Release PR
2.51.0 (2026-07-30)
Full Changelog: v2.50.0...v2.51.0
Features
Bug Fixes
This pull request is managed by Stainless's GitHub App.
The semver version number is based on included commit messages. Alternatively, you can manually set the version number in the title of this pull request.
For a better experience, it is recommended to use either rebase-merge or squash-merge when merging this pull request.
🔗 Stainless website
📚 Read the docs
🙋 Reach out for help or questions