Skip to content

Conversation

@Light2Dark
Copy link
Contributor

@Light2Dark Light2Dark commented Sep 29, 2025

📝 Summary

Typically, the base URL is https://<your-resource-name>.azure.com

For Azure, we also need the deployment_name and api_version. So we pad that in to the base_url.

We expect: https://<your-resource-name>.openai.azure.com/openai/deployments/<deployment_name>?api-version=<api-version>.

Referenced issue: #3117

Also fixes #6368 by disabling reasoning_mode param. According to docs, they are only enabled for custom models set up in Azure Foundry. We can expose this as a param in the future.

🔍 Description of Changes

📋 Checklist

  • I have read the contributor guidelines.
  • For large changes, or changes that affect the public API: this change was discussed or approved through an issue, on Discord, or the community discussions (Please provide a link if applicable).
  • I have added tests for the changes made.
  • I have run the code and verified that it works as expected.

@vercel
Copy link

vercel bot commented Sep 29, 2025

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

Project Deployment Preview Comments Updated (UTC)
marimo-docs Ready Ready Preview Comment Sep 29, 2025 6:06pm

@github-actions github-actions bot added the documentation Improvements or additions to documentation label Sep 29, 2025
@mscolnick mscolnick merged commit affaa95 into main Sep 29, 2025
16 checks passed
@mscolnick mscolnick deleted the sham/support-azure-models branch September 29, 2025 18:14
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

documentation Improvements or additions to documentation merge when ready

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Unable to use the Azure OpenAI provider with GPT-5 or o3

3 participants