GPT-5 return reasoning content via /chat/completions + GPT-5-Codex working on Claude Code

[krrishdholakia]

Title

1. GPT-5 return reasoning content

Specify openai/responses prefix, to tell litellm to call the Responses API

response = litellm.completion(
    model="openai/responses/gpt-5-mini", # tells litellm to call the model via the Responses API
    messages=[{"role": "user", "content": "What is the capital of France?"}],
    reasoning_effort="low",
)

2. Working gpt-5-codex via claude code

Relevant issues

Closes LIT-925
Closes LIT-1088

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
• I have added a screenshot of my new test passing locally
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem

Type

🆕 New Feature
🛠️ Bug Fixes

Changes

Chat Completion -> Responses API Bridge:

• return reasoning content from responses api
• convert tool calls from chat completion to responses api spec
• don't pass invalid user str to responses api (len > 64 char)
• don't pass invalid stream_options param to responses api (include_usage)

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Preview	Comments	Updated (UTC)
litellm	Ready	Preview	Comment	Oct 11, 2025 2:53am