Azure OpenAI: Deployment Issue with GPT-5.6-Luna Model Despite Available Quota

Problem description

I am unable to deploy the GPT-5.6-Luna model (version 2026-07-09) with the GlobalStandard deployment type in Azure OpenAI, even though the quota appears sufficient when checked via commands in Cloud Shell. The portal shows an error indicating no resource locations with sufficient quota, which contradicts the quota data. I need assistance understanding this discrepancy and how to successfully deploy the model.

Environment

Azure OpenAI in Microsoft Foundry (formerly AOAI Studio).

What I've already tried

I verified quota and capacity using Azure CLI and ARM APIs, which show the limit of 15,000 tokens per minute (TPM) and available capacity in multiple regions. I confirmed that my subscription has Azure OpenAI access enabled and the Contributor role assigned. I attempted to create the deployment from the portal, but the error persists, and the discrepancy between quota API data and portal validation remains.

Current status

I am seeking guidance on how to reconcile the conflicting information between the quota data and portal validation, and instructions on the correct steps to allocate quota and deploy the GPT-5.6-Luna model in the desired region.