Use OpenAI models through Azure’s infrastructure. Learn more here.

Azure OpenAI provides access to OpenAI’s models like GPT-4o, o3-mini, and more.

​
Authentication

Navigate to Azure OpenAI on the Azure Portal and create a service. Then, using the Azure AI Studio portal, create a deployment and set your environment variables:

export AZURE_OPENAI_API_KEY=***
export AZURE_OPENAI_ENDPOINT=***  # Of the form https://<your-resource-name>.openai.azure.com/openai/deployments/<your-deployment-name>
# Optional:
# export AZURE_OPENAI_DEPLOYMENT=***

​
Example

Use AzureOpenAI with your Agent:

from agno.agent import Agent
from agno.models.azure import AzureOpenAI
from os import getenv

agent = Agent(
    model=AzureOpenAI(id="gpt-4o"),
    markdown=True
)

# Print the response on the terminal
agent.print_response("Share a 2 sentence horror story.")

​
Prompt caching

Prompt caching will happen automatically using our AzureOpenAI model. You can read more about how OpenAI handle caching in their docs.

​
Advanced Examples

View more examples here.

​
Parameters

ParameterTypeDefaultDescription
idstr-The specific model ID used for generating responses. This field is required.
namestr"AzureOpenAI"The name identifier for the agent.
providerstr"Azure"The provider of the model.
api_keyOptional[str]"None"The API key for authenticating requests to the Azure OpenAI service.
api_versionstr"2024-10-21"The version of the Azure OpenAI API to use.
azure_endpointOptional[str]"None"The endpoint URL for the Azure OpenAI service.
azure_deploymentOptional[str]"None"The deployment name or ID in Azure.
azure_ad_tokenOptional[str]"None"The Azure Active Directory token for authenticating requests.
azure_ad_token_providerOptional[Any]"None"The provider for obtaining Azure Active Directory tokens.
openai_clientOptional[AzureOpenAIClient]"None"An instance of AzureOpenAIClient provided for making API requests.

AzureOpenAI also supports the parameters of OpenAI.