skills.rest
jgezelscorp
jgezelscorpCOMMUNITY
Explore all skills by this author →
GitHub

deploy-model

Deploy Azure OpenAI models with preset or custom configurations and capacity discovery.

Updated Apr 11, 2026
Search Tags:#azure#customization#openai#model deployment#capacity discovery
One-click install
npx skills add https://github.com/jgezelscorp/Apex --skill deploy-model-jgezelscorp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deploy-model
Source: https://github.com/jgezelscorp/Apex/tree/main/.github/skills/microsoft-foundry/models/deploy-model
Command: npx skills add https://github.com/jgezelscorp/Apex --skill deploy-model-jgezelscorp

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the deployment of Azure OpenAI models, providing intelligent intent-based routing, quick preset deployments, fully customized deployments, and capacity discovery across regions and projects.

Core Features & Use Cases

  • Intelligent Intent-Based Routing: Analyzes user intent and routes to the appropriate deployment mode (preset, customize, or capacity discovery).
  • Quick Preset Deployments: Quickly deploy models to optimal regions with sensible defaults.
  • Fully Customized Deployments: Offers control over version, SKU, capacity, RAI policy, and advanced options.
  • Capacity Discovery: Identifies available capacity across regions and projects based on user-defined requirements.
  • Use Case: A user wants to deploy the GPT-4 model with custom settings, specifying the version, SKU, capacity, and RAI policy.

Quick Start

Use the deploy-model skill to deploy a custom GPT-4 model with the following settings: version="gpt-4", SKU="GlobalStandard", capacity="50K TPM", RAI policy="Microsoft.Prompt-Shield".

Frequently Asked Questions about deploy-model

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

FAQPage Schema
How do I deploy Azure OpenAI models with custom settings?▼

You can deploy Azure OpenAI models with custom settings by specifying parameters like version, SKU, capacity, and RAI policy to configure the model exactly as needed. This allows full control over the deployment configuration.

Do I need the Azure CLI to deploy OpenAI models?▼

Yes, you need the Azure CLI and an active Azure subscription to automate the deployment of Azure OpenAI models. The CLI is required to execute the deployment commands and manage resource configurations.

How can I check Azure OpenAI capacity across regions before deployment?▼

You can check Azure OpenAI capacity by running a capacity discovery process across regions and projects. This identifies available capacity based on your defined requirements before you commit to a deployment.

What is the fastest way to deploy an Azure OpenAI model?▼

The fastest way is using quick preset deployments, which automatically route to optimal regions using sensible default settings. This allows you to deploy models quickly without manually configuring individual parameters.

Can I specify an RAI policy when deploying GPT-4 on Azure?▼

Yes, you can apply a specific RAI policy, such as Microsoft.Prompt-Shield, during custom deployments. This gives you control over the responsible AI configurations applied to your GPT-4 model.

Related Skills

Explore More Software Engineering Skills→
qprjack86qprjack86

capacity

Discover Azure OpenAI model capacity across regions and projects.

Community
Advanced
alexdcdalexdcd
46

openrouter

Route requests across 400+ AI models with automatic failover via a unified API.

Community
Advanced
dgethingsdgethings

azure-network-ops

Audit and manage Azure network configurations and security controls across VNets, NSGs, and gateways.

Community
Advanced
githubgithub
37.6k

azure-deployment-preflight

Validate Azure Bicep templates and permissions with what-if analysis.

Official
Advanced