How to beginner · 3 min read

Azure OpenAI supported models

Q: Azure OpenAI supported models

Azure OpenAI supports models such as gpt-4o, gpt-4o-mini, gpt-4.1, and gpt-4.1-mini under custom deployment names. You must use your Azure deployment name when calling the API via the AzureOpenAI client. Model names differ from OpenAI’s public API and require specifying the deployment name in model parameter.

Quick answer

Azure OpenAI supports models such as gpt-4o, gpt-4o-mini, gpt-4.1, and gpt-4.1-mini under custom deployment names. You must use your Azure deployment name when calling the API via the AzureOpenAI client. Model names differ from OpenAI’s public API and require specifying the deployment name in model parameter.

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 higher. Set environment variables for your Azure OpenAI API key and endpoint URL. Use the AzureOpenAI client from the openai package to authenticate.

bash

pip install openai>=1.0

Step by step

Use your Azure OpenAI deployment name as the model parameter. The deployment name corresponds to the model you deployed in your Azure portal (e.g., gpt-4o-deployment). Below is a complete example to call the chat completion endpoint.

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"],  # e.g., "gpt-4o-deployment"
    messages=[{"role": "user", "content": "Hello from Azure OpenAI!"}]
)

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

output

Hello from Azure OpenAI! How can I assist you today?

Common variations

You can use different deployment names for other supported models like gpt-4o-mini or gpt-4.1. Streaming responses are supported by passing stream=True to chat.completions.create(). Async usage requires an async client or wrapper. Always use the deployment name, not the raw model name.

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": "Stream a response from Azure OpenAI."}],
        stream=True
    )

    async for chunk in response:
        print(chunk.choices[0].delta.get("content", ""), end="", flush=True)

asyncio.run(main())

output

Streaming response text appears here in chunks...

Troubleshooting

If you get a ModelNotFound error, verify your deployment name matches exactly the one in the Azure portal.
Ensure your AZURE_OPENAI_ENDPOINT includes the full URL, e.g., https://your-resource-name.openai.azure.com/.
Check that your API key has permissions for the Azure OpenAI resource.

✅

Key Takeaways

Always use your Azure deployment name as the model parameter in API calls.
Supported models include gpt-4o, gpt-4o-mini, gpt-4.1, and gpt-4.1-mini under custom deployments.
Use the AzureOpenAI client with azure_endpoint and api_version parameters for authentication.
Streaming and async calls are supported with the same deployment name model parameter.
Verify environment variables and deployment names carefully to avoid common errors.

Verified 2026-04 · gpt-4o, gpt-4o-mini, gpt-4.1, gpt-4.1-mini

Verify ↗