> ## Documentation Index
> Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Azure AI Foundry

> Learn how to use Azure AI Foundry models in Agno.

Use various open source models hosted on Azure's infrastructure. Learn more [here](https://learn.microsoft.com/azure/ai-services/models).

Azure AI Foundry provides access to models like `Phi`, `Llama`, `Mistral`, `Cohere` and more.

## Authentication

Navigate to Azure AI Foundry on the [Azure Portal](https://portal.azure.com/) and create a service. Then set your environment variables:

<CodeGroup>
  ```bash Mac theme={null}
  export AZURE_API_KEY=***
  export AZURE_ENDPOINT=***  # Of the form https://<your-host-name>.<your-azure-region>.models.ai.azure.com/models
  # Optional:
  # export AZURE_API_VERSION=***
  ```

  ```bash Windows theme={null}
  setx AZURE_API_KEY ***  # Of the form https://<your-host-name>.<your-azure-region>.models.ai.azure.com/models
  setx AZURE_ENDPOINT ***
  # Optional:
  # setx AZURE_API_VERSION ***
  ```
</CodeGroup>

## Example

Use `AzureAIFoundry` with your `Agent`:

<CodeGroup>
  ```python agent.py theme={null}
  from agno.agent import Agent
  from agno.models.azure import AzureAIFoundry

  agent = Agent(
      model=AzureAIFoundry(id="Phi-4"),
      markdown=True
  )

  # Print the response on the terminal
  agent.print_response("Share a 2 sentence horror story.")
  ```
</CodeGroup>

## Advanced Examples

View more examples [here](../examples/models/azure/ai_foundry).

## Parameters

<Snippet file="model-azure-ai-foundry-params.mdx" />

`AzureAIFoundry` is a subclass of the [Model](/reference/models/model) class and has access to the same params.