Azure AI Foundry: Capacity Unavailability for GPT-5.6 and GPT-5.4 Models — Quota Requests Denied

Problem description

I am experiencing issues with deploying current-generation models in Azure AI Foundry. Despite having active credits and submitting multiple quota requests for GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, and GPT-5.4 Mini across various regions and deployment types, all requests have been denied due to capacity unavailability. My subscription still shows 0 TPM for these models, and I need approximately 100 KTPM for my workloads related to R&D, agentic coding, and scientific research.

Environment

Azure AI Foundry model quota in the affected subscription, specific models include GPT-5.6 Sol, Terra, Luna, and GPT-5.4 Mini, across Global Standard and EUR Data Zone Standard regions.

What I've already tried

I reviewed the quota guidance for Foundry, checked my existing quota allocations, and submitted multiple capacity requests for the models and regions of interest. All requests were denied due to capacity limitations. I have also been advised that quota requests are handled separately from capacity availability, and no manual quota enablement has been identified.

Current status

I am seeking a human review or escalation to determine if there is available capacity for the models and regions I require, or if quota can be manually enabled for GPT-5.6 Sol or Terra. I want guidance on how to proceed given the capacity constraints and the repeated denials of my quota requests.