capacity

Discover Azure OpenAI model capacity across regions and projects.

Updated May 25, 2026
One-click install
npx skills add https://github.com/AcendWay/ai-skills-library --skill capacity-acendway
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: capacity
Source: https://github.com/AcendWay/ai-skills-library/tree/main/skill-folders/microsoft-foundry/models/deploy-model/capacity
Command: npx skills add https://github.com/AcendWay/ai-skills-library --skill capacity-acendway

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires az, jq, python3, and includes scripts (resource) components.

What problem does it solve?

Finds where you can deploy an Azure OpenAI model by discovering available capacity across regions and matching it with your subscription’s quota so you avoid quota-related deployment failures.

Core Features & Use Cases

  • Azure model capacity discovery across all accessible regions and projects, producing a ranked availability table.
  • Subscription quota validation per candidate region to ensure capacity is actually usable for your account.
  • Decision-ready ranking that orders results by capacity fit, quota availability, and number of existing projects in the region.
  • Use cases: “where can I deploy gpt-4o?”, “which regions have enough TPM?”, and “best region and project for a specific model/version.”

Quick Start

Ask the AI to run the capacity discovery for a model by saying: "Discover Azure OpenAI capacity for gpt-4o version 2025-01-31 with a minimum of 10000 TPM, and rank the best regions I can use based on both capacity and my subscription quota."

Frequently Asked Questions about capacity

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check Azure OpenAI capacity and quota across regions before deploying a model?

To check Azure OpenAI capacity across regions, query modelCapacities for a specific model and version, cross-reference subscription usage quotas by location, and produce a ranked table of deployable regions to prevent quota-related deployment failures.

What is the best way to find which Azure regions have enough TPM for gpt-4o?

The best way to find regions with enough TPM is to run capacity discovery across accessible regions and projects, specifying a minimum TPM requirement to rank locations by capacity fit, quota availability, and existing project count.

Do I need Azure CLI authentication to discover available OpenAI model capacity?

Yes, Azure CLI authentication is required to discover available OpenAI model capacity. The discovery process requires using Azure CLI to query modelCapacities and cross-reference subscription usage quotas by location across accessible regions.

Why does my Azure OpenAI deployment fail due to quota restrictions in my chosen region?

Azure OpenAI deployments fail when a region has model capacity but your subscription lacks the quota to use it. Cross-referencing modelCapacities with subscription usage quota by location identifies actually deployable regions.

Can I compare Azure OpenAI model availability and quota across multiple subscriptions?

You can compare Azure OpenAI model availability and quota across accessible regions and projects by applying quota-aware region comparison, producing a decision-ready ranking that orders results by capacity fit and quota availability.