Azure OpenAI
Configure Azure OpenAI Service to access OpenAI models deployed on Microsoft Azure through Braintrust.
Authentication
Choose between two authentication methods:
- API Key: Use an Azure OpenAI API key for authentication
- Entra API (Azure AD): Use Azure Active Directory (Entra ID) for authentication
Configuration
| Field | Description |
|---|---|
| API base URL String | Required. Your Azure OpenAI service endpoint URL in the format https://{resource-name}.openai.azure.com. Documentation |
Authentication typeapi_key | entra_api | Optional. Choose between API key or Entra API authentication. Default is api_key. Documentation |
| API version String | Optional. The API version to use for requests. Default is 2023-07-01-preview. Documentation |
| Deployment String | Optional. The deployment name for your model (if using named deployments). Documentation |
| No named deployment Boolean | Optional. Whether to skip using deployment names in the request path. Default is false. If true, the deployment name will not be used in the request path. |
Models
Azure OpenAI provides access to OpenAI models including:
- GPT-4o
gpt-4o - GPT-4
gpt-4 - GPT-3.5 Turbo
gpt-35-turbo - DALL-E 3
dall-e-3 - Whisper
whisper
Note: Model availability varies by region and requires deployment through the Azure portal.
Setup requirements
- Azure OpenAI Resource: Create an Azure OpenAI service resource in the Azure portal
- Model Deployment: Deploy the models you want to use through the Azure portal
- API Access: Obtain your API key or configure Entra ID authentication
- Regional Availability: Ensure your chosen region supports the models you need