feat(openai): Add support for reasoning_effort='none' in GPT-5.1

[Chesars]

Title

Add support for reasoning_effort='none' in GPT-5.1

Relevant issues

Fixes #16633

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

Summary

OpenAI's GPT-5.1 introduced a new reasoning_effort="none" parameter value which replaces the previous "minimal" setting for faster, lower-latency responses. This is
now the default setting for GPT-5.1. This PR adds full support for this new parameter value.

Details

Code:

• Updated REASONING_EFFORT type in litellm/types/llms/openai.py to include "none" value
• The type now supports: Literal["none", "minimal", "low", "medium", "high"]

Documentation:

• Updated docs/my-website/docs/providers/openai.md to include GPT-5.1, GPT-5-mini, and GPT-5-nano models
• Added documentation showing "none" as GPT-5.1's default reasoning effort
• Clarified that "none" replaces "minimal" in the GPT-5.1 model family

Tests:

• Added test_gpt5_1_reasoning_effort_none() test that verifies:
  • reasoning_effort="none" passes through correctly
  • Other valid values ("low", "medium", "high") continue to work
• All existing tests continue to pass (15/15)

Tests

tests/test_litellm/llms/openai/test_gpt5_transformation.py::test_gpt5_1_reasoning_effort_none PASSED [100%]

All GPT-5 transformation tests pass:

Related Documentation

Reference: OpenAI GPT-5.1 Documentation

[vercel]

@Chesars is attempting to deploy a commit to the CLERKIEAI Team on Vercel.

A member of the Team first needs to authorize it.

[ishaan-jaff]

lgtm

[JamesHutchison]

Does this support the temperature parameter as well? I do not see that in the test.

    def map_openai_params(
        self,
        non_default_params: dict,
        optional_params: dict,
        model: str,
        drop_params: bool,
    ) -> dict:
        ################################################################
        # max_tokens is not supported for gpt-5 models on OpenAI API
        # Relevant issue: https://github.com/BerriAI/litellm/issues/13381
        ################################################################
        if "max_tokens" in non_default_params:
            optional_params["max_completion_tokens"] = non_default_params.pop(
                "max_tokens"
            )

        if "temperature" in non_default_params:
            temperature_value: Optional[float] = non_default_params.pop("temperature")
            if temperature_value is not None:
                if temperature_value == 1:
                    optional_params["temperature"] = temperature_value
                elif litellm.drop_params or drop_params:
                    pass
                else:
                    raise litellm.utils.UnsupportedParamsError(
                        message=(
                            "gpt-5 models (including gpt-5-codex) don't support temperature={}. Only temperature=1 is supported. To drop unsupported params set `litellm.drop_params = True`"
                        ).format(temperature_value),
                        status_code=400,
                    )

[Chesars]

Hi @JamesHutchison Thanks, you're right, GPT 5.1 added support for temp, top_p and logprobs if reasoning_effort=none. PR #17011 is in progress.