# Deploy Model > Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create). Source: https://skillsagentes.com/skills/microsoft/azure-skills/deploy-model Repository: https://github.com/microsoft/azure-skills Author: microsoft License: MIT Updated: hace 4 días Context cost: 162 tok installed, 1.8k tok once triggered, 26.1k tok with every bundled file Bundle: 17 files, 102 KB Permissions requested: none declared ## Install ```bash npx -y skills add microsoft/azure-skills --skill deploy-model --agent claude-code ``` ## What it does - Es el skill unificado de despliegue de modelos de Azure OpenAI, con enrutado por intención. - Cubre tres caminos: despliegue rápido con preset, despliegue totalmente personalizado (versión, SKU, capacidad, política RAI) y descubrimiento de capacidad entre regiones y proyectos. - Crea los despliegues **fuera de banda**, vía CLI de Azure, MCP o portal. - Para proyectos Foundry gestionados por azd, el propio archivo indica declarar los despliegues en `azure.yaml` en vez de usar este skill. ## Use it when - Se quiere desplegar o aprovisionar un modelo de Azure OpenAI. - Se quiere encontrar capacidad, comprobar disponibilidad o saber en qué región desplegar. ## Don't bother when - Para listar despliegues existentes, borrarlos, crear agentes o crear proyectos: el archivo remite a otras herramientas. ## What triggers it - "despliega gpt en Azure OpenAI" - "¿dónde puedo desplegar este modelo?" - "crea un deployment de modelo" ## Before you install - Para proyectos scaffoldados con `azd ai agent init`, los despliegues se declaran en `azure.yaml` y los crea `azd provision` vía Bicep. - Environment: BASE_URL, DEPLOYMENT_NAME, DEPLOYMENT_PATH, ENCODED_PATH, ENCODED_SUB, FOUNDRY_RESOURCE, GUID_HEX, PROJECT_NAME, RESOURCE_GROUP, SUBSCRIPTION_ID ## Files - SKILL.md — 7 KB - TEST_PROMPTS.md — 3 KB - capacity/SKILL.md — 7 KB - capacity/scripts/discover_and_rank.ps1 — 5 KB - capacity/scripts/discover_and_rank.sh — 5 KB - capacity/scripts/query_capacity.ps1 — 3 KB - capacity/scripts/query_capacity.sh — 3 KB - customize/EXAMPLES.md — 4 KB - customize/SKILL.md — 9 KB - customize/references/customize-guides.md — 3 KB - customize/references/customize-workflow.md — 13 KB - preset/EXAMPLES.md — 3 KB - preset/SKILL.md — 5 KB - preset/references/preset-workflow.md — 22 KB - preset/references/workflow.md — 6 KB - scripts/generate_deployment_url.ps1 — 2 KB - scripts/generate_deployment_url.sh — 3 KB ## SKILL.md Reproduced verbatim from microsoft/azure-skills under MIT. This section is the upstream document and is in English. # Deploy Model > **Scope — read this first.** This skill creates model deployments **out-of-band** via Azure CLI / MCP / portal. For azd-managed Foundry projects (those scaffolded from `azd ai agent init`), declare deployments in `azure.yaml services.ai-project.deployments[]` instead — `azd ai agent init` writes the entry from the sample manifest and `azd provision` creates the deployment through Bicep. See [foundry-agent/create/create-hosted.md](../../foundry-agent/create/create-hosted.md) for the Golden Path. Use this skill only for: (a) Foundry projects not managed by an azd project, (b) ad-hoc deployments outside the azd lifecycle. Unified entry point for all Azure OpenAI model deployment workflows. Analyzes user intent and routes to the appropriate deployment mode. ## Quick Reference | Mode | When to Use | Sub-Skill | |------|-------------|-----------| | **Preset** | Quick deployment, no customization needed | [preset/SKILL.md](preset/SKILL.md) | | **Customize** | Full control: version, SKU, capacity, RAI policy | [customize/SKILL.md](customize/SKILL.md) | | **Capacity Discovery** | Find where you can deploy with specific capacity | [capacity/SKILL.md](capacity/SKILL.md) | ## Intent Detection Analyze the user's prompt and route to the correct mode: ``` User Prompt │ ├─ Simple deployment (no modifiers) │ "deploy gpt-4o", "set up a model" │ └─> PRESET mode │ ├─ Customization keywords present │ "custom settings", "choose version", "select SKU", │ "set capacity to X", "configure content filter", │ "PTU deployment", "with specific quota" │ └─> CUSTOMIZE mode │ ├─ Capacity/availability query │ "find where I can deploy", "check capacity", │ "which region has X capacity", "best region for 10K TPM", │ "where is this model available" │ └─> CAPACITY DISCOVERY mode │ └─ Ambiguous (has capacity target + deploy intent) "deploy gpt-4o with 10K capacity to best region" └─> CAPACITY DISCOVERY first → then PRESET or CUSTOMIZE ``` ### Routing Rules | Signal in Prompt | Route To | Reason | |------------------|----------|--------| | Just model name, no options | **Preset** | User wants quick deployment | | "custom", "configure", "choose", "select" | **Customize** | User wants control | | "find", "check", "where", "which region", "available" | **Capacity** | User wants discovery | | Specific capacity number + "best region" | **Capacity → Preset** | Discover then deploy quickly | | Specific capacity number + "custom" keywords | **Capacity → Customize** | Discover then deploy with options | | "PTU", "provisioned throughput" | **Customize** | PTU requires SKU selection | | "optimal region", "best region" (no capacity target) | **Preset** | Region optimization is preset's specialty | ### Multi-Mode Chaining Some prompts require two modes in sequence: **Pattern: Capacity → Deploy** When a user specifies a capacity requirement AND wants deployment: 1. Run **Capacity Discovery** to find regions/projects with sufficient quota 2. Present findings to user 3. Ask: "Would you like to deploy with **quick defaults** or **customize settings**?" 4. Route to **Preset** or **Customize** based on answer > 💡 **Tip:** If unsure which mode the user wants, default to **Preset** (quick deployment). Users who want customization will typically use explicit keywords like "custom", "configure", or "with specific settings". ## Project Selection (All Modes) Before any deployment, resolve which project to deploy to. This applies to **all** modes (preset, customize, and after capacity discovery). ### Resolution Order 1. **Check `PROJECT_RESOURCE_ID` env var** — if set, use it as the default 2. **Check user prompt** — if user named a specific project or region, use that 3. **If neither** — query the user's projects and suggest the current one ### Confirmation Step (Required) **Always confirm the target before deploying.** Show the user what will be used and give them a chance to change it: ``` Deploying to: Project: Region: Resource: Is this correct? Or choose a different project: 1. ✅ Yes, deploy here (default) 2. 📋 Show me other projects in this region 3. 🌍 Choose a different region ``` If user picks option 2, show top 5 projects in that region: ``` Projects in : 1. project-alpha (rg-alpha) 2. project-beta (rg-beta) 3. project-gamma (rg-gamma) ... ``` > ⚠️ **Never deploy without showing the user which project will be used.** This prevents accidental deployments to the wrong resource. ## Pre-Deployment Validation (All Modes) Before presenting any deployment options (SKU, capacity), always validate both of these: 1. **Model supports the SKU** — query the model catalog to confirm the selected model+version supports the target SKU: ```bash az cognitiveservices model list --location --subscription -o json ``` Filter for the model, extract `.model.skus[].name` to get supported SKUs. 2. **Subscription has available quota** — check that the user's subscription has unallocated quota for the SKU+model combination: ```bash az cognitiveservices usage list --location --subscription -o json ``` Match by usage name pattern `OpenAI..` (e.g., `OpenAI.GlobalStandard.gpt-4o`). Compute `available = limit - currentValue`. > ⚠️ **Warning:** Only present options that pass both checks. Do NOT show hardcoded SKU lists — always query dynamically. SKUs with 0 available quota should be shown as ❌ informational items, not selectable options. > 💡 **Quota management:** For quota increase requests, usage monitoring, and troubleshooting quota errors, defer to the [quota skill](../../quota/quota.md) instead of duplicating that guidance inline. ## Prerequisites All deployment modes require: - Azure CLI installed and authenticated (`az login`) - Active Azure subscription with deployment permissions - Microsoft Foundry project resource ID (or agent will help discover it via `PROJECT_RESOURCE_ID` env var) ## Sub-Skills - **[preset/SKILL.md](preset/SKILL.md)** — Quick deployment to optimal region with sensible defaults - **[customize/SKILL.md](customize/SKILL.md)** — Interactive guided flow with full configuration control - **[capacity/SKILL.md](capacity/SKILL.md)** — Discover available capacity across regions and projects --- Skills Agentes — https://skillsagentes.com/skills/microsoft/azure-skills/deploy-model