Skip to content

Conversation

@Chesars
Copy link
Contributor

@Chesars Chesars commented Dec 1, 2025

Relevant issues & PRs

Fixes #17309, #17071
#17071

Pre-Submission checklist

  • I have Added testing in the tests/litellm/ directory
  • 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

🐛 Bug Fix

Changes

Allow reasoning_effort='none' for Azure gpt-5.1 models.

Files Changed

  • litellm/llms/azure/chat/gpt_5_transformation.py
  • tests/test_litellm/llms/azure/chat/test_azure_gpt5_transformation.py

Details

Azure documentation confirms reasoning_effort='none' is supported for gpt-5.1:
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning

"none is only supported for gpt-5.1"

Test

  • All 16 tests pass in test_azure_gpt5_transformation.py

PR BerriAI#17071 drops or errors on reasoning_effort='none' for all GPT models.
It doesn't actually allow 'none' to be sent to Azure for gpt-5.1 which
supports it according to Azure documentation.

See: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning
"none is only supported for gpt-5.1"
@vercel
Copy link

vercel bot commented Dec 1, 2025

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

A member of the Team first needs to authorize it.

"Azure OpenAI does not support reasoning_effort='none'. "
"Azure OpenAI does not support reasoning_effort='none' for this model. "
"Supported values are: 'low', 'medium', and 'high'. "
"Note: gpt-5.1 does support reasoning_effort='none'. "
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we need this statement

Copy link
Contributor Author

@Chesars Chesars Dec 2, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Optional. We could keep it or remove it, It informs users trying reasoning_effort='none' on unsupported models that gpt-5.1 is an alternative that does support it.

Copy link
Collaborator

@Sameerlite Sameerlite left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

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

2 participants