skills.rest
sohamda
sohamdaCOMMUNITY
Explore all skills by this author →
Website𝕏@iamsohamGitHub

preset

Deploys Azure OpenAI models to regions with available capacity using Azure CLI.

Updated May 12, 2026
Search Tags:#model deployment#multi-region#azure cli#azure openai#ai foundry#capacity check#cognitive services
One-click install
npx skills add https://github.com/sohamda/apex-try-out-demo-repo --skill preset-sohamda
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: preset
Source: https://github.com/sohamda/apex-try-out-demo-repo/tree/main/.archive/_archived_skills/microsoft-foundry/models/deploy-model/preset
Command: npx skills add https://github.com/sohamda/apex-try-out-demo-repo --skill preset-sohamda

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Deploying Azure OpenAI models often fails because the current region lacks quota or capacity, forcing users to manually check regions, find or create AI Foundry projects, and retry deployments. This Skill automates that entire capacity-aware deployment workflow. ## Core Features & Use Cases - Capacity-Aware Deployment: Checks the current project's region first, then queries all Azure regions for available GlobalStandard capacity and presents alternatives. - Project Discovery and Creation: Filters existing AI Foundry projects by region or creates a new AI Services hub and project when none exist. - Multi-Format Model Support: Handles OpenAI models via Azure CLI and Anthropic models via the ARM REST API with required modelProviderData (industry, country code, organization name). - Use Case: You need to deploy gpt-4o but West US 2 has no quota. The Skill queries all regions, lets you pick East US 2 with 120K TPM available, and completes the deployment in about two minutes. ## Quick Start Ask the agent to deploy gpt-4o to the Azure region with the best available capacity for your AI Foundry project.

Frequently Asked Questions about preset

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

FAQPage Schema
How do I deploy an Azure OpenAI model when my region has no capacity?▼

Query the modelCapacities REST API across all regions to find available GlobalStandard capacity, then select a region and deploy there. This Skill automates that flow, including finding or creating an AI Foundry project in the chosen region.

How to check Azure OpenAI model capacity by region with Azure CLI?▼

Use az rest to call the Microsoft.CognitiveServices modelCapacities endpoint with your subscription, model name, version, and format. The response lists availableCapacity per region for the GlobalStandard SKU.

Can I deploy Anthropic models like claude-sonnet with Azure CLI?▼

Azure CLI does not support the modelProviderData field required by Anthropic models. You must deploy via the ARM REST API with industry, country code, and organization name in the request body, using capacity 1 for MaaS billing.

What happens if no Azure region has quota for my model?▼

The deployment fails gracefully with guidance: request a quota increase via the quota skill, review existing deployments consuming quota, or switch to an alternative model such as gpt-4o-mini with lower capacity requirements.

When should I not use the preset deployment skill?▼

Avoid it when you need custom SKU selection, specific model version pinning, custom capacity values, or PTU (provisioned throughput) deployments. Those scenarios require the customize skill instead.

Related Skills

Explore More Software Engineering Skills→
microsoftmicrosoft
2.9k

preset

Deploy Azure OpenAI models by checking regional capacity and selecting the best option.

Official
Advanced
microsoftmicrosoft
242

microsoft-foundry

Discover, deploy, and manage Microsoft Foundry AI resources with Python SDK and MCP tools.

Official
Advanced
microsoftmicrosoft
1.4k

azure-quotas

Checks Azure quota limits, usage, and available capacity across resource providers and regions.

Official
Intermediate
iinoshirozhengiinoshirozheng

customize

Guide Azure OpenAI model deployments with version, SKU, capacity, and RAI policy configuration.

Community
Advanced