deploy-model

Name: deploy-model
Availability: InStock
Author: Soham

Deploys Azure OpenAI models with intent-based routing across preset, customize, and capacity discovery modes.

Updated May 12, 2026

Search Tags:#quota #model deployment #azure cli #azure openai #capacity discovery #ai foundry #sku configuration

Ready to run

npx skills add https://github.com/sohamda/apex-try-out-demo-repo --skill deploy-model-sohamda

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: deploy-model
Source: https://github.com/sohamda/apex-try-out-demo-repo/tree/main/.archive/_archived_skills/microsoft-foundry/models/deploy-model
Command: npx skills add https://github.com/sohamda/apex-try-out-demo-repo --skill deploy-model-sohamda

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Deploying Azure OpenAI models requires navigating SKUs, versions, capacity quotas, regions, and content filter policies, which is error-prone and time-consuming when done manually through the Azure CLI or portal. ## Core Features & Use Cases - Intent-Based Routing: Analyzes your prompt and routes to the right mode — quick preset deployment, fully customized deployment, or capacity discovery across regions. - Capacity Discovery: Queries all regions and projects to find where a model can be deployed with sufficient quota, presenting a ranked table of options. - Guided Customization: Walks through version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy, and advanced options like dynamic quota and spillover. - Use Case: Ask "find the best region to deploy gpt-4o with 50K TPM" and the skill discovers capacity, confirms the target project, and deploys with your chosen settings. ## Quick Start Ask the agent to deploy gpt-4o and it will confirm your project, check capacity, and create the deployment with sensible defaults.

Frequently Asked Questions about deploy-model

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

FAQPage Schema

How do I deploy an Azure OpenAI model with the Azure CLI?▼

Use az cognitiveservices account deployment create with the model name, version, format, SKU, and capacity. This skill automates that flow by checking authentication, validating quota, and monitoring the deployment until it succeeds.

How do I find which Azure regions have capacity for gpt-4o?▼

Run the capacity discovery mode, which queries the modelCapacities REST API across all regions, cross-references your subscription quota and existing projects, and outputs a ranked table of regions meeting your TPM target.

What is the difference between GlobalStandard and ProvisionedManaged SKUs?▼

GlobalStandard is TPM-based pay-per-use suited for production with high availability, while ProvisionedManaged (PTU) reserves guaranteed throughput at fixed cost for predictable high-volume workloads. PTU deployments require a minimum of 50 units.

Can I deploy Anthropic models like Claude to Azure AI Foundry?▼

Yes, Anthropic models are deployed via the ARM REST API with a modelProviderData payload containing industry, country code, and organization name. They use capacity of 1 under MaaS billing and do not support RAI policies.

Why does my model deployment fail with a quota exceeded error?▼

The error occurs when your subscription has no unallocated quota for the SKU and model combination in that region. Check usage with az cognitiveservices usage list, try another region, or request a quota increase through the quota skill.