deploy-model

Name: deploy-model
Availability: InStock
Author: MoonAxis

Route Azure OpenAI model deployment requests to preset, custom, or capacity discovery workflows.

Updated Aug 23, 2026

Search Tags:#model deployment #ai services #provisioning #azure openai #capacity discovery #custom configuration

Ready to run

npx skills add https://github.com/MoonAxis/azure-stack --skill deploy-model

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: deploy-model
Source: https://github.com/MoonAxis/azure-stack/tree/main/skills/microsoft-foundry/models/deploy-model
Command: npx skills add https://github.com/MoonAxis/azure-stack --skill deploy-model

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill simplifies the complex process of deploying Azure OpenAI models, whether you need a quick setup or a highly customized configuration, ensuring models are deployed efficiently and correctly.

Core Features & Use Cases

Unified Deployment: Acts as a single entry point for all Azure OpenAI model deployment needs.
Intelligent Routing: Analyzes user intent to route to the appropriate deployment mode (Preset, Customize, Capacity Discovery).
Capacity Discovery: Helps find available capacity across regions and projects.
Customization: Allows detailed configuration of model version, SKU, capacity, and RAI policies.
Use Case: Deploying a new GPT-4o model for a customer-facing application, ensuring it has the right capacity and configuration for optimal performance and cost-efficiency.

Quick Start

Use the deploy-model skill to deploy gpt-4o with default settings to the best available region.

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 configuration?▼

To deploy Azure OpenAI models with custom configuration, you can use the customize workflow to specify model version, SKU, capacity, and RAI policies across various Azure regions and projects.

What is capacity discovery for Azure OpenAI deployment?▼

Capacity discovery for Azure OpenAI deployment is a workflow that helps you find available model capacity across different Azure regions and projects to ensure efficient provisioning.

Can I use a single interface for all my Azure OpenAI provisioning needs?▼

Yes, you can use a unified deployment interface that intelligently routes your Azure OpenAI provisioning requests to preset, custom, or capacity discovery workflows based on your intent.

What's the best way to deploy a GPT-4o model to the best available Azure region?▼

The best way to deploy a GPT-4o model to the best available region is to use the preset deployment workflow, which applies default settings to automatically route your request for optimal availability.

Does this Azure OpenAI deployment approach support RAI policy configuration?▼

Yes, this Azure OpenAI deployment approach supports RAI policy configuration, allowing you to define detailed custom settings alongside model version, SKU, and capacity during your provisioning process.