# Deploy Model

> Skill unificado de despliegue de modelos de Azure OpenAI con enrutado por intención: despliegues rápidos con preset, despliegues personalizados y descubrimiento de capacidad entre regiones y proyectos.

Fuente: https://skillsagentes.com/skills/microsoft/azure-skills/deploy-model
Markdown: https://skillsagentes.com/skills/microsoft/azure-skills/deploy-model.md

Repositorio: https://github.com/microsoft/azure-skills
Autor: microsoft
Licencia: MIT
Actualizado: el mes pasado
Coste de contexto: 162 tok instalada, 1.8k tok al activarse, 26.1k tok con todos los archivos del bundle
Bundle: 17 archivos, 102 KB
Permisos que pide: ninguno declarado

## Instalación

Un skill son archivos markdown: los mismos archivos valen para cualquier agente y lo único que cambia es el directorio de destino, es decir la bandera `--agent`. Añade `-g` para instalarlo en todos los proyectos de la máquina.

```bash
# Claude Code
npx -y skills add microsoft/azure-skills --skill deploy-model --agent claude-code
# Cursor
npx -y skills add microsoft/azure-skills --skill deploy-model --agent cursor
# Codex
npx -y skills add microsoft/azure-skills --skill deploy-model --agent codex
# Gemini CLI
npx -y skills add microsoft/azure-skills --skill deploy-model --agent gemini
# Windsurf
npx -y skills add microsoft/azure-skills --skill deploy-model --agent windsurf
# Cline
npx -y skills add microsoft/azure-skills --skill deploy-model --agent cline
```

## Qué hace

- 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.

## Cuándo usarla

- Se quiere desplegar o aprovisionar un modelo de Azure OpenAI.
- Se quiere encontrar capacidad, comprobar disponibilidad o saber en qué región desplegar.

## Cuándo no

- Para listar despliegues existentes, borrarlos, crear agentes o crear proyectos: el archivo remite a otras herramientas.

## Qué la activa

- "despliega gpt en Azure OpenAI"
- "¿dónde puedo desplegar este modelo?"
- "crea un deployment de modelo"

## Antes de instalar

- Para proyectos scaffoldados con `azd ai agent init`, los despliegues se declaran en `azure.yaml` y los crea `azd provision` vía Bicep.
- Variables de entorno: BASE_URL, DEPLOYMENT_NAME, DEPLOYMENT_PATH, ENCODED_PATH, ENCODED_SUB, FOUNDRY_RESOURCE, GUID_HEX, PROJECT_NAME, RESOURCE_GROUP, SUBSCRIPTION_ID
- makes network requests
- reads environment config

## Archivos

- 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

Reproducido tal cual desde microsoft/azure-skills bajo MIT. Esta sección es el documento original y está en inglés.

# 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:  <project-name>
  Region:   <region>
  Resource: <resource-group>

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 <region>:
  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 <region> --subscription <sub-id> -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 <region> --subscription <sub-id> -o json
   ```
   Match by usage name pattern `OpenAI.<SKU>.<model-name>` (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

## Dónde encaja

- Categoría: [DevOps e infraestructura](https://skillsagentes.com/categorias/devops-infraestructura.md) — Despliegues, contenedores, IaC y flujos de gestión de incidentes.
- Creador: [microsoft](https://skillsagentes.com/creators/microsoft.md) — 43 skills en el directorio
- [Todas las skills](https://skillsagentes.com/skills.md)
- [Ranking de instalaciones](https://skillsagentes.com/ranking.md)

## Otras skills del mismo repositorio

- [Microsoft Foundry](https://skillsagentes.com/skills/microsoft/azure-skills/microsoft-foundry.md): Despliega, evalúa, ajusta y gestiona agentes de Foundry de punta a punta con azd: agentes hospedados, evaluación por lotes y continua, optimizador de prompts y fine-tuning (SFT/DPO/RFT).
- [Azure Prepare](https://skillsagentes.com/skills/microsoft/azure-skills/azure-prepare.md): Prepara proyectos Azure basados en azd para desplegar: genera azure.yaml, la infraestructura (Bicep o Terraform) y los Dockerfiles del flujo del Azure Developer CLI.
- [Azure Diagnostics](https://skillsagentes.com/skills/microsoft/azure-skills/azure-diagnostics.md): Depura incidencias de producción en Azure con AppLens, Azure Monitor, resource health y triaje seguro. Cubre App Service, Container Apps, Functions, AKS, VMs y mensajería.
- [Azure Validate](https://skillsagentes.com/skills/microsoft/azure-skills/azure-validate.md): Validación previa al despliegue en Azure. Comprueba en profundidad la configuración, la infraestructura (Bicep o Terraform), los roles RBAC, los permisos de identidad administrada y los prerrequisitos.
- [Azure App Onboard](https://skillsagentes.com/skills/microsoft/azure-skills/azure-app-onboard.md): Orquestador de punta a punta: de una idea o una app existente hasta un despliegue en Azure, con estimación de costes y aprobación previa. Analiza tu app y detecta los servicios adecuados.

---

Skills Agentes · [Índice de páginas en markdown](https://skillsagentes.com/sitemap.md) · [Inicio](https://skillsagentes.com/index.md)