How to beginner · 3 min read

Azure OpenAI SDK installation

Q: Azure OpenAI SDK installation

Install the openai Python package (version 1.0 or higher) using pip. Then, create an AzureOpenAI client with your Azure endpoint and API key from environment variables to start calling Azure OpenAI models.

Quick answer

Install the openai Python package (version 1.0 or higher) using pip. Then, create an AzureOpenAI client with your Azure endpoint and API key from environment variables to start calling Azure OpenAI models.

PREREQUISITES

Python 3.8+
Azure OpenAI API key
Azure OpenAI endpoint URL
pip install openai>=1.0

Setup

Install the official openai Python package version 1.0 or later. Set your Azure OpenAI API key and endpoint as environment variables for secure access.

bash

pip install openai>=1.0

Step by step

Use the AzureOpenAI class from the openai package to create a client. Pass your API key and Azure endpoint URL from environment variables. Call chat.completions.create with your deployment name and messages to get a response.

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 SDK!"}]
)

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

output

Hello from Azure OpenAI SDK!

Common variations

Use different deployment names by changing the model parameter.
Enable streaming by passing stream=True to chat.completions.create.
Use async calls with asyncio and await if your environment supports it.

python

import asyncio
import os
from openai import AzureOpenAI

async def main():
    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 call example"}]
    )

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

asyncio.run(main())

output

Async call example response text

Troubleshooting

If you see authentication errors, verify your AZURE_OPENAI_API_KEY and AZURE_OPENAI_ENDPOINT environment variables are set correctly.
Ensure your deployment name matches the model parameter exactly.
Check your network connectivity to the Azure endpoint.

✅

Key Takeaways

Use the official openai Python package version 1.0+ for Azure OpenAI integration.
Set AZURE_OPENAI_API_KEY and AZURE_OPENAI_ENDPOINT environment variables before running code.
Create an AzureOpenAI client and call chat.completions.create with your deployment name.
Support for async and streaming calls is available via the SDK.
Verify environment variables and deployment names to avoid common errors.

Verified 2026-04 · gpt-4o, gpt-4o-mini

Verify ↗