Skip to content

[Bug]: Azure's gpt-5.1 fails when reasoning_effort="none" which is supported based on docs #17309

@mijalapenos

Description

@mijalapenos

What happened?

Calling Azure's gpt-5.1 with reasoning_effort="none" and temperature=0 fails with exception. However, Azure's documentation now explicitly states reasoning_effort="none" is supported (only) for gpt-5.1:
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning?view=foundry-classic&tabs=csharp%2Cgpt-5#new-gpt-5-reasoning-features

This has been introduced by #17071

Relevant log output

litellm.exceptions.UnsupportedParamsError: litellm.UnsupportedParamsError: Azure OpenAI does not support reasoning_effort='none'. Supported values are: 'low', 'medium', and 'high'. To drop this parameter, set `litellm.drop_params=True` or for proxy:

`litellm_settings:
 drop_params: true`
Issue: https://github.com/BerriAI/litellm/issues/16704

Are you a ML Ops Team?

Yes

What LiteLLM version are you on ?

v1.80.7-nightly

Twitter / LinkedIn details

No response

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions