capacity

Discover Azure OpenAI model capacity across regions and projects via Azure CLI.

Updated Jul 3, 2025
One-click install
npx skills add https://github.com/isakawar/crmKvitkovaPovnya --skill capacity-isakawar
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: capacity
Source: https://github.com/isakawar/crmKvitkovaPovnya/tree/main/.agents/skills/microsoft-foundry/models/deploy-model/capacity
Command: npx skills add https://github.com/isakawar/crmKvitkovaPovnya --skill capacity-isakawar

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

It eliminates the guesswork of where Azure OpenAI models can actually be deployed by identifying regions and projects with sufficient available capacity and effective subscription quota.

Core Features & Use Cases

  • Capacity discovery across regions: Finds available Azure OpenAI model capacity across all accessible regions and filters for a minimum target (e.g., TPM requirements).
  • Quota-aware recommendations: Cross-references platform capacity with subscription quota/usage limits to highlight where deployment is realistically possible.
  • Project-aware ranking: Counts accessible AI Foundry projects by region and ranks results to support faster, more compatible deployment decisions.
  • Use cases: Choose best regions for capacity, troubleshoot quota errors by switching to alternative regions, and plan multi-project deployment coverage.

Quick Start

Ask the AI to run capacity discovery for your model by saying: “Find available Azure OpenAI capacity for gpt-4o with at least 10000 TPM and recommend the best regions and projects I can use.”

Frequently Asked Questions about capacity

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

FAQPage Schema
How do I find Azure OpenAI capacity across regions for a specific model?

To find Azure OpenAI capacity across regions, you can use a capacity discovery tool that checks accessible regions and filters them against a minimum TPM target. It cross-references platform availability with subscription quota to produce a ranked shortlist of viable deployment locations.

What is the best way to troubleshoot Azure OpenAI quota errors during deployment planning?

The best way to troubleshoot Azure OpenAI quota errors is to run quota validation across accessible regions. By analyzing capacity and subscription limits, you can identify alternative regions or AI Foundry projects with sufficient quota to satisfy your TPM requirements.

How does quota analysis work when checking Azure OpenAI model availability?

Quota analysis for Azure OpenAI model availability works by cross-referencing discovered platform capacity with your effective subscription usage limits. This process highlights regions where deployment is realistically possible, excluding areas that fail capacity or quota constraints.

Do I need Azure CLI authentication to check available Azure OpenAI TPM capacity?

Yes, you need Azure CLI authentication to check available Azure OpenAI TPM capacity. The capacity discovery process uses read-only Azure REST calls authenticated via Azure CLI to safely query regions and projects without handling actual deployments.

Can I compare Azure OpenAI capacity across multiple AI Foundry projects?

Yes, you can compare Azure OpenAI capacity across multiple AI Foundry projects. The capacity discovery process counts accessible projects by region and ranks the results, supporting faster and more compatible multi-project deployment coverage decisions.

What are the limitations of using capacity discovery for Azure OpenAI deployment planning?

The main limitation of capacity discovery is that it explicitly avoids handling actual deployments. It only performs read-only checks to produce a ranked shortlist of feasible regions and projects, meaning you must deploy the Azure OpenAI models manually afterward.