No Quotum for GPT-6 Luna or GPT-5.6 Luna

Rafael Backx 0 Reputation points
2026-10-10T11:58:26.1166667+00:00

Title: Unable to obtain quota for GPT-6 Luna or GPT-5.6 Luna in Azure AI Foundry — all regions show 0 capacity

Hi everyone,

Has anyone recently managed to obtain quota for GPT-6 Luna or GPT-5.6 Luna in Azure AI Foundry?

I'm relatively new to Azure and currently migrating from AWS Bedrock. My goal is to host these models in a European Azure region to reduce the latency we're experiencing with Bedrock's global inference endpoint.

However, I'm unable to obtain any quota for either model.

Here's what I've tried so far:

Created an Azure AI Foundry resource in Germany West Central.

Confirmed that both models appear in the Foundry model catalog.

Attempted to request additional quota through the Azure quota request form.

Received repeated rejections stating: "The region you requested a quota increase in is not available to expand capacity at this time."

Queried Azure's Model Capacities API, which returned 0 available capacity across all listed regions for GPT-6 Luna.

Confirmed that I have Owner permissions at the subscription level.

I'm trying to understand whether this is a temporary capacity limitation, a subscription eligibility issue, or something else I'm missing.

Has anyone successfully deployed either of these models recently? If so, which region and deployment type did you use?

Is there another way to obtain initial quota, even just for development and testing?

Any guidance would be greatly appreciated. Thanks!

Foundry Models
Foundry Models

A catalog of AI models in Microsoft Foundry that you can discover, compare, and deploy using Azure’s built‑in tools for evaluation, fine‑tuning, and inference

0 comments

2 answers

Sort by: Newest
Most helpful Newest Oldest
  1. kagiyama yutaka 5,575 Reputation points
    2026-10-11T03:47:19.52+00:00

    I think those results show available capacity, not when more will become available.

    Check Foundry (new) → Manage → Quota for matching model/version, region and deployment type. Since your requests were rejected, ask Azure Support about an initial allocation and possible ETA. Include the rejection reference and quota limit.

    GlobalStandard can process inference globally, even with a German resource. DataZoneStandard in the EU keeps inference within the EU data zone, not Germany alone.

    Was this answer helpful?

    0 comments
  2. Salamat Shah 830 Reputation points MVP
    2026-10-10T15:37:00.7966667+00:00

    The repeated quota request rejections and 0 available capacity across regions indicate a temporary service-capacity constraint rather than a configuration problem in your subscription.

    Recommendation:

    • Verify that GPT-6 Luna / GPT-5.6 Luna are supported in your target Azure region.
    • If the Model Capacities API shows 0 capacity across all regions, Microsoft currently has no available quota to allocate.
    • Owner permissions do not guarantee quota approval.
    • Try alternative supported regions and deployment types if available.
    • Submit a quota request or Azure Support ticket and wait for capacity to become available.
    • For development/testing, consider using another available model until quota opens up.

    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.