Skip to content

[BUG] Cannot use azure/gpt-6-astra model due to max_tokens parameter #12981

Closed

Description

@kjm0202

OmniRoute Version

3.8.50

Installation Method

Docker / Docker Compose

Operating System

Linux

OS Version

Ubuntu 24.04 LTS

Node.js Version

No response

Provider(s) Involved

Azure OpenAI

Model(s) Involved

azure/gpt-6-astra

Client Tool

Testing with Playground

Description

Whenever I tried to validate azure/gpt-6-astra in OmniRoute, it just says 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead..

Other models including azure/gpt-5.6 series are working normal.

Steps to Reproduce

  1. Enter Azure OpenAI key
  2. Test gpt-6-astra in playground

Expected Behavior

Work as normal

Actual Behavior

Error occurs

Test Impact

Unsure

Error Logs / Output

'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.

Screenshots

Image

Additional Context

No response

Validation Plan

No response

Activity

  1. changed the title [-][BUG] Cannot use `azure/gpt-6-astra` models due to wrong parameter[/-] [+][BUG] Cannot use `azure/gpt-6-astra` model due to `max_tokens` parameter[/+] on Sep 7, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions