How to beginner · 3 min read

How to get Azure OpenAI endpoint and key

Quick answer

To get your Azure OpenAI endpoint and API key, sign in to the Azure Portal, create or select an Azure OpenAI resource, then find the endpoint URL on the resource overview page and the API keys under the Keys and Endpoint section. Use these values to configure your client with AzureOpenAI SDK or REST API calls.

PREREQUISITES

Python 3.8+
Azure subscription
Azure OpenAI resource created in Azure Portal
pip install openai>=1.0
AzureOpenAI API key and endpoint from Azure Portal

Setup Azure OpenAI resource

First, sign in to the Azure Portal. Navigate to Create a resource and search for Azure OpenAI. Follow the prompts to create a new Azure OpenAI resource in your desired subscription and region. After deployment, open the resource page.

Find endpoint and API key

On your Azure OpenAI resource page, locate the Overview tab to find the Endpoint URL. Then, go to the Keys and Endpoint section to view your API keys. Copy the Endpoint and one of the Keys to use in your application.

Location	What to find
Overview tab	Endpoint URL (e.g., https://your-resource-name.openai.azure.com/)
Keys and Endpoint tab	API keys (Key1 and Key2)

Use endpoint and key in Python

Set environment variables for your AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_API_KEY. Then use the AzureOpenAI client from the openai package to authenticate and call the API.

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

Use managed identity authentication instead of API key by passing azure_ad_token_provider to AzureOpenAI.
Change api_version if Azure updates the API.
Use different deployment names for model parameter as configured in Azure.

Troubleshooting

If you get authentication errors, verify your API key and endpoint are correct and not expired.
Ensure your Azure OpenAI resource is in a supported region.
Check that your deployment name matches the model parameter in code.

✅

Key Takeaways

Get your Azure OpenAI endpoint URL and API key from the Azure Portal resource page.
Use environment variables to securely store and access your Azure OpenAI credentials in Python.
Use the AzureOpenAI client from the openai package with correct api_version and deployment name.
Verify your resource region and deployment names to avoid authentication and usage errors.

Verified 2026-04 · gpt-4o, AzureOpenAI

Verify ↗