GPT-5.6-terra Global Standard quota unavailable in Southeast Asia

Sunay H 0 Reputation points
2026-10-07T06:46:31.3233333+00:00

We are trying to deploy the gpt-5.6-terra model in Microsoft Foundry / Azure OpenAI in the Southeast Asia region.

The model appears in the deployment catalog and we can select Global Standard as the deployment type. However, when we try to select the resource location, Southeast Asia is shown as "no quota", and the deployment cannot be completed.

Azure OpenAI in Foundry Models
0 comments No comments

1 answer

Sort by: Most helpful
  1. AI answer

    2026-10-07T06:46:51.1+00:00

    gpt-5.6-terra with Global Standard is listed as available in Southeast Asia, so the region/model combination itself is supported.

    If the deployment UI shows "no quota" for Southeast Asia, the blocker is quota allocation rather than model availability.

    Supported next checks:

    1. In Azure AI Foundry portal, go to Management > Quota and review the quota for gpt-5.6-terra in Southeast Asia.
    2. Check whether quota is already assigned to existing deployments for that model in that region. Foundry assigns quota per region, per model in Tokens-per-Minute (TPM), and creating deployments consumes that quota.
    3. If quota is fully allocated, either:
      • reallocate TPM from other existing deployments, or
      • request more quota using the quota increase form.
    4. If no visible deployment is consuming quota but the portal still shows no quota, this matches cases where quota can remain allocated or out of sync after prior deployment activity. In that case, open a Microsoft Support request for backend quota allocation review.
    5. As a workaround, try another supported region for Global Standard if deployment is urgent.

    Relevant facts for this scenario:

    • Southeast Asia is supported for Global Standard deployments of gpt-5.6-terra.
    • Foundry quota is assigned per subscription, per region, per model.
    • Deployments consume TPM quota, and new deployments fail when that quota is exhausted.
    • If quota is exceeded, the documented actions are to request more quota or reallocate TPM from existing deployments.

    References:

    AI-generated content may be incorrect. Read our transparency notes for more information.

    Was this answer helpful?

Your answer

Answers can be marked as 'Accepted' by the question author and 'Recommended' by moderators, which helps users know the answer solved the author's problem.