An Azure service that provides access to OpenAI’s GPT-3 models with enterprise capabilities.
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:
- In Azure AI Foundry portal, go to Management > Quota and review the quota for gpt-5.6-terra in Southeast Asia.
- 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.
- If quota is fully allocated, either:
- reallocate TPM from other existing deployments, or
- request more quota using the quota increase form.
- 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.
- 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: