deploy-model

Automate Azure OpenAI model deployment with intent-based routing and customization.

6|2|Updated Jan 29, 2026
One-click install
npx skills add https://github.com/jonathan-vella/azure-smb-rf --skill deploy-model-jonathan-vella
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deploy-model
Source: https://github.com/jonathan-vella/azure-smb-rf/tree/main/.github/skills/microsoft-foundry/models/deploy-model
Command: npx skills add https://github.com/jonathan-vella/azure-smb-rf --skill deploy-model-jonathan-vella

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill simplifies the deployment of Azure OpenAI models, providing intelligent routing and customizable deployment options to streamline the process.

Core Features & Use Cases

  • Unified Deployment: Offers a single point of entry for all model deployment workflows.
  • Intelligent Routing: Analyzes user intent and routes to the appropriate deployment mode (preset, customize, capacity discovery).
  • Customization: Full control over model version, SKU, capacity, RAI policy, and advanced options.
  • Capacity Discovery: Identifies regions and projects with available capacity for the model.
  • Use Case: Deploy an OpenAI model with specific requirements or find the best region and project for a given capacity.

Quick Start

To deploy a model, use the 'deploy-model' skill and follow the prompts to select the mode, specify settings, and confirm the deployment.

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 intelligent routing?

Azure OpenAI model deployment uses intelligent routing to analyze user intent and direct workflows to preset, customize, or capacity discovery modes. This streamlines configuration by matching your deployment strategy to specific model version, SKU, and capacity requirements automatically.

Do I need Azure CLI to deploy and configure Azure OpenAI models?

Yes, Azure CLI is a required dependency for deploying Azure OpenAI models. You must have it installed and configured alongside your AI Foundry project resources to execute the deployment scripts and apply the intelligent routing configurations successfully.

Can I customize Azure OpenAI deployment settings for SKU and RAI policy?

Yes, Azure OpenAI deployments support full customization of model version, SKU, capacity, and RAI policy. The customize mode provides granular control over these advanced deployment options to meet specific project requirements and compliance standards.

What's the best way to find available capacity for Azure OpenAI models?

Capacity discovery mode identifies regions and projects with available capacity for your target Azure OpenAI model. It analyzes deployment options to find the best location and project resources for hosting models based on current availability.

How does intelligent routing work for Azure OpenAI model deployment?

Intelligent routing analyzes your deployment intent and automatically routes the workflow to the appropriate mode: preset for quick setups, customize for detailed configurations, or capacity discovery for finding available regions and project resources.

What AI Foundry resources are required to deploy Azure OpenAI models?

Deploying Azure OpenAI models requires existing AI Foundry project resources provisioned in your Azure environment. These resources provide the foundational infrastructure needed for the deployment scripts to execute and configure intelligent routing successfully.