skills.rest
paidethon
paidethonCOMMUNITY
Explore all skills by this author →
GitHub

deploy-model

Automate Azure OpenAI model deployment across regions with custom versions, capacities, and RAI policies.

Updated Apr 9, 2026
Search Tags:#azure#customization#openai#model deployment#capacity discovery
One-click install
npx skills add https://github.com/paidethon/Daily --skill deploy-model-paidethon
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deploy-model
Source: https://github.com/paidethon/Daily/tree/main/.agents/skills/microsoft-foundry/models/deploy-model
Command: npx skills add https://github.com/paidethon/Daily --skill deploy-model-paidethon

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, enabling users to deploy with ease, customize settings, and discover available capacity across regions.

Core Features & Use Cases

  • Unified Deployment: Simplifies the process of deploying Azure OpenAI models through a single skill.
  • Customization: Offers full customization for deployment, including model version, SKU, capacity, and RAI policy.
  • Capacity Discovery: Helps users find the best region and project for deploying models based on available capacity.
  • Use Case: Deploy a GPT-4 model with custom settings, such as specifying the version, SKU, and capacity, to meet specific application requirements.

Quick Start

Deploy a GPT-4 model with custom settings: deploy-model customize --model-name gpt-4 --sku-name GlobalStandard --capacity 50K

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 across multiple regions and SKUs?▼

To deploy Azure OpenAI models, you can automate the process across various regions and SKUs while customizing model versions, capacities, and RAI policies. This requires Azure CLI authentication and access to Azure AI Foundry resources.

Can I customize the model version and capacity when deploying GPT-4 on Azure?▼

Yes, you can fully customize Azure OpenAI deployments by specifying the model version, SKU, and capacity. For example, use a command like `customize --model-name gpt-4 --sku-name GlobalStandard --capacity 50K` to meet your requirements.

What is the best way to discover available capacity for Azure OpenAI deployments?▼

The best way to discover available capacity is to use a deployment automation tool that scans regions and projects. This helps you find the optimal location for deploying Azure OpenAI models based on current resource availability.

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

Yes, Azure CLI authentication is required to deploy Azure OpenAI models. You must also have appropriate access to Azure AI Foundry resources to automate deployments and configure settings across regions successfully.

How do I configure RAI policies during Azure OpenAI model deployment?▼

You can configure RAI policies during Azure OpenAI model deployment by using deployment customization features. This allows you to apply specific Responsible AI policies alongside your chosen model version, SKU, and capacity settings.

Related Skills

Explore More Software Engineering Skills→
paulanunes85paulanunes85
1

ai-foundry-operations

Provision Azure AI Foundry resources and deploy OpenAI models via Terraform.

Community
Advanced
hsliuustc0106hsliuustc0106
84

vllm-omni-api

Bridge client applications with the vLLM-Omni API using OpenAI-compatible endpoints.

Community
Intermediate
virtualrusselvirtualrussel
1

dt-obs-azure

Query Azure APIs to inspect resource configurations, security posture, and performance metrics.

Community
Advanced
h4vzzh4vzz
33

infrastructure-as-code

Generate Terraform, Pulumi, CloudFormation, or CDK configurations for cloud infrastructure.

Community
Advanced