Azure OpenAI o1

Configure an Agno agent to use Azure OpenAI's o1 model for reasoning tasks.

This example uses non-streaming output. Azure o1 does not stream; o3 streaming requires eligible access. See Azure reasoning support. Set the deployment variable to a deployment of the model used below.

Add the following code to your Python file

azure_openai.py
from agno.agent import Agent
from agno.models.azure.openai_chat import AzureOpenAI

agent = Agent(model=AzureOpenAI(id="o1"))
agent.print_response(
    "Solve the trolley problem. Evaluate multiple ethical frameworks. "
    "Include an ASCII diagram of your solution.",
    stream=False,
)

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Install dependencies

uv pip install -U openai agno

Set your Azure OpenAI credentials

  export AZURE_OPENAI_API_KEY="xxx"
  export AZURE_OPENAI_ENDPOINT="xxx"
  export AZURE_OPENAI_DEPLOYMENT="xxx"

Run Agent

python azure_openai.py