release: 0.35.0

[stainless-app]

Automated Release PR

0.35.0 (2025-11-18)

Full Changelog: v0.34.1...v0.35.0

Features

• api: api update (d6ec93d)
• api: api update (48c8f11)

Bug Fixes

• update chat completion streaming types (833cf83)

Chores

• GitHub Terraform: Create/Update .github/workflows/code-freeze-bypass.yaml [skip ci] (63d11e3)

---

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

---

Note

Release 0.35.0 with expanded chat completion/streaming types (Groq-specific metadata, MCP tool listing, usage breakdown) and detailed token usage metrics.

• Types (chat/completions):
  • Add Groq-specific metadata XGroq (incl. debug, seed, usage), usage_breakdown, and service_tier to chat_completion (x_groq, UsageBreakdown*).
  • Introduce MCP tool listing types (McpListTool*) and ChatCompletion.mcp_list_tools.
  • Update streaming chat_completion_chunk:
    • Expand XGroq (defaults, debug, seed, usage_breakdown, improved error).
    • Add x_groq on chunks and UsageBreakdown* models.
• Usage metrics:
  • Extend CompletionUsage with completion_tokens_details and prompt_tokens_details.
• Release/meta:
  • Bump version to 0.35.0, update OpenAPI spec refs, and update CHANGELOG.md.

^{Written by Cursor Bugbot for commit ba8f9f1. This will update automatically on new commits. Configure here.}

[stainless-app]

🧪 Testing

    To try out this version of the SDK, run:
    ```
    pip install 'https://pkg.stainless.com/s/groqcloud-python/833cf83b5f2f59eaa17507c330be90a722a871e8/groq-0.34.1-py3-none-any.whl'
    ```

    _Expires: Thu, 18 Dec 2025 23:42:08 GMT_

[cursor]

Bug: Incorrect Field Requirement Breaks Validation

The reasoning_tokens field in CompletionTokensDetails is defined as required but should be optional since it's only present for reasoning models. This causes validation errors when parsing responses from non-reasoning models that don't include this field.

 

[stainless-app]

🤖 Release is at https://github.com/groq/groq-python/releases/tag/v0.35.0 🌻