> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/MicrosoftDocs/azure-ai-docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Foundry Models Overview

> Explore Microsoft Foundry's comprehensive model catalog including Azure OpenAI, Foundry Direct, partner, and community models.

# Foundry Models Overview

Microsoft Foundry Models is your destination for discovering, evaluating, and deploying AI models for building agents, copilots, and AI applications.

## Model Catalog

Access **1900+ models** from Microsoft, OpenAI, and leading AI companies:

<CardGroup cols={2}>
  <Card title="Models Sold Directly by Azure" icon="microsoft">
    Hosted and sold by Microsoft with direct support, SLAs, and deep Azure integration
  </Card>

  <Card title="Partner & Community Models" icon="users">
    Specialized models from Anthropic, Meta, Cohere, Hugging Face, and more
  </Card>
</CardGroup>

## Model Categories

### Foundation Models

* **GPT-4o**: Multimodal reasoning and generation
* **GPT-4**: Advanced language understanding
* **Claude**: Long-context processing (200K tokens)
* **Llama 3**: Open-source alternative

### Reasoning Models

* Multi-step problem solving
* Mathematical reasoning
* Code generation and analysis

### Small Language Models (SLMs)

* **Phi-3 family**: Efficient edge deployment
* Lower latency and cost
* Specialized tasks

### Multimodal Models

* Process text and images
* Vision and language combined
* Examples: GPT-4o, Claude 3

## Deployment Options

<Tabs>
  <Tab title="Serverless API">
    * Pay-per-token billing
    * Instant scaling
    * No capacity management
    * Best for: Development, variable workloads
  </Tab>

  <Tab title="Provisioned Throughput">
    * Reserved model capacity
    * Predictable performance and cost
    * Fungible across compatible models
    * Best for: Production, high-volume
  </Tab>

  <Tab title="Managed Compute">
    * Deploy to dedicated VMs
    * Open-source model support
    * Full control
    * Best for: Custom deployments
  </Tab>
</Tabs>

## Model Selection Guide

<Steps>
  <Step title="Define Requirements">
    Task, inputs, outputs, latency needs
  </Step>

  <Step title="Check Capabilities">
    Input types, context length, features
  </Step>

  <Step title="Evaluate Performance">
    Benchmarks, testing with your use case
  </Step>

  <Step title="Assess Cost">
    Token costs, volume estimates
  </Step>

  <Step title="Verify Availability">
    Regional availability, lifecycle status
  </Step>
</Steps>

## Key Features

* **Tool Calling**: GPT-4o, GPT-4, Claude 3
* **JSON Mode**: Structured output guarantee
* **Vision**: Image processing (GPT-4o, Claude)
* **Streaming**: Incremental response delivery
* **Fine-Tuning**: Customize with your data

See [Model Deployment](/foundry/models/deployment) and [Region Support](/foundry/models/region-support) for details.