How to beginner · 3 min read

How to configure Azure OpenAI environment variables

Q: How to configure Azure OpenAI environment variables

Set the AZURE_OPENAI_API_KEY, AZURE_OPENAI_ENDPOINT, and AZURE_OPENAI_DEPLOYMENT environment variables to configure Azure OpenAI in your Python environment. These variables enable the AzureOpenAI client to authenticate and target the correct deployment when calling the API.

Quick answer

Set the AZURE_OPENAI_API_KEY, AZURE_OPENAI_ENDPOINT, and AZURE_OPENAI_DEPLOYMENT environment variables to configure Azure OpenAI in your Python environment. These variables enable the AzureOpenAI client to authenticate and target the correct deployment when calling the API.

PREREQUISITES

Python 3.8+
Azure OpenAI resource with deployed model
pip install openai>=1.0
Azure OpenAI API key and endpoint URL

Setup environment variables

Configure the following environment variables in your system or development environment to use Azure OpenAI with the Python SDK:

AZURE_OPENAI_API_KEY: Your Azure OpenAI API key.
AZURE_OPENAI_ENDPOINT: The endpoint URL of your Azure OpenAI resource, e.g., https://your-resource-name.openai.azure.com/.
AZURE_OPENAI_DEPLOYMENT: The deployment name of the model you want to use, as configured in the Azure portal.

Set these variables in your shell or IDE before running your Python code.

bash

export AZURE_OPENAI_API_KEY="your_azure_openai_api_key"
export AZURE_OPENAI_ENDPOINT="https://your-resource-name.openai.azure.com/"
export AZURE_OPENAI_DEPLOYMENT="your-deployment-name"

Step by step Python example

Use the AzureOpenAI client from the openai package to authenticate using the environment variables and send a chat completion request.

python

import os
from openai import AzureOpenAI

client = AzureOpenAI(
    api_key=os.environ["AZURE_OPENAI_API_KEY"],
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    api_version="2024-02-01"
)

response = client.chat.completions.create(
    model=os.environ["AZURE_OPENAI_DEPLOYMENT"],
    messages=[{"role": "user", "content": "Hello from Azure OpenAI!"}]
)

print(response.choices[0].message.content)

output

Hello from Azure OpenAI!

Common variations

You can customize your Azure OpenAI usage with these variations:

Async calls: Use asyncio with AzureOpenAI for asynchronous requests.
Different API versions: Change the api_version parameter to match your Azure resource version.
Streaming responses: Use streaming parameters if supported by your deployment.

python

import asyncio
from openai import AzureOpenAI

async def async_chat():
    client = AzureOpenAI(
        api_key=os.environ["AZURE_OPENAI_API_KEY"],
        azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
        api_version="2024-02-01"
    )
    response = await client.chat.completions.acreate(
        model=os.environ["AZURE_OPENAI_DEPLOYMENT"],
        messages=[{"role": "user", "content": "Async hello!"}]
    )
    print(response.choices[0].message.content)

asyncio.run(async_chat())

output

Async hello!

Troubleshooting tips

If you get authentication errors, verify your AZURE_OPENAI_API_KEY and AZURE_OPENAI_ENDPOINT are correct and have no trailing spaces.
If the deployment name is invalid, check your Azure portal for the exact deployment name and update AZURE_OPENAI_DEPLOYMENT.
Ensure your environment variables are loaded in the shell or IDE session where you run your Python script.

✅

Key Takeaways

Always set AZURE_OPENAI_API_KEY, AZURE_OPENAI_ENDPOINT, and AZURE_OPENAI_DEPLOYMENT environment variables before using Azure OpenAI SDK.
Use the AzureOpenAI client with these variables to authenticate and specify the deployment model.
Verify environment variables are correctly loaded in your runtime environment to avoid authentication or deployment errors.

Verified 2026-04 · gpt-4o, AzureOpenAI

Verify ↗