Azure AI Foundry

Use various open source models hosted on Azure’s infrastructure. Learn more here. Azure AI Foundry provides access to models like Phi, Llama, Mistral, Cohere and more.

Authentication

Navigate to Azure AI Foundry on the Azure Portal and create a service. Then set your environment variables:

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=***

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 ***

Example

Use AzureAIFoundry with your Agent:

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.")

Advanced Examples

View more examples here.

Parameters

Parameter	Type	Default	Description
`id`	`str`	-	The specific model ID used for generating responses. This field is required.
`name`	`str`	`"AzureOpenAI"`	The name identifier for the agent.
`provider`	`str`	`"Azure"`	The provider of the model.
`api_key`	`Optional[str]`	`"None"`	The API key for authenticating requests to the Azure OpenAI service.
`api_version`	`str`	`"2024-10-21"`	The version of the Azure OpenAI API to use.
`azure_endpoint`	`Optional[str]`	`"None"`	The endpoint URL for the Azure OpenAI service.
`client`	`Optional[ChatCompletionsClient]`	`None`	The client for making requests to the Azure OpenAI service.
`async_client`	`Optional[AsyncChatCompletionsClient]`	`None`	The asynchronous client for making requests to the Azure OpenAI service.
`temperature`	`Optional[float]`	`None`	Controls randomness in the model's output. Higher values make output more random.
`max_tokens`	`Optional[int]`	`None`	The maximum number of tokens to generate in the response.
`frequency_penalty`	`Optional[float]`	`None`	Reduces repetition by penalizing tokens based on their frequency.
`presence_penalty`	`Optional[float]`	`None`	Reduces repetition by penalizing tokens that have appeared at all.
`top_p`	`Optional[float]`	`None`	Controls diversity by limiting cumulative probability of tokens considered.
`stop`	`Optional[Union[str, List[str]]]`	`None`	Sequences where the model will stop generating further tokens.
`seed`	`Optional[int]`	`None`	Random seed for deterministic outputs.
`model_extras`	`Optional[Dict[str, Any]]`	`None`	Additional model-specific parameters.
`request_params`	`Optional[Dict[str, Any]]`	`None`	Additional parameters to pass with the request.
`timeout`	`Optional[float]`	`None`	Timeout in seconds for API requests.
`max_retries`	`Optional[int]`	`None`	Maximum number of retries for failed requests.
`http_client`	`Optional[httpx.Client]`	`None`	Custom HTTP client for making requests.
`client_params`	`Optional[Dict[str, Any]]`	`None`	Additional parameters for client configuration.

AzureAIFoundry is a subclass of the Model class and has access to the same params.

Introduction

Concepts

Other

How to

Azure AI Foundry

Authentication

Example

Advanced Examples

Parameters

​Authentication

​Example

​Advanced Examples

​Parameters

Authentication

Example

Advanced Examples

Parameters