Skip to main content
Watch: I Built an AI App Without Leaving Databricks

API compatibility - 2 documented limits

Microsoft Foundry / Azure OpenAI API compatibility

Microsoft Foundry / Azure OpenAI documents an OpenAI-compatible API at https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/ (responses and chat/completions). Its Anthropic-compatible base URL, the value for ANTHROPIC_BASE_URL, is https://<resource name>.services.ai.azure.com/anthropic, and it serves Claude models only. The docs list 2 limitations: 1 for the OpenAI-compatible layer and 1 for the Anthropic-compatible layer.

Verified against Microsoft Foundry / Azure OpenAI's own documentation. Not documented means the docs read that day do not say; it never means No.

Compare every provider in the API compatibility matrix.

OpenAI-compatible API

Supported
Base URL
https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/
Endpoints
  • responses
  • chat/completions
Auth
api-key: $AZURE_OPENAI_API_KEY (REST) or the key as the OpenAI client's api_key; or Authorization: Bearer <Microsoft Entra ID token>
Regional and alternate URLs
  • Azure OpenAIhttps://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/
  • Foundryhttps://YOUR-RESOURCE-NAME.services.ai.azure.com/openai/v1/
Notes
The v1 API (opt-in since August 2025) uses the standard OpenAI() client with no api-version parameter. model is your deployment name. Chat completions also work with other providers' models sold by Azure (for example DeepSeek, Grok, MAI-DS-R1). Responses API is recommended for Azure OpenAI models.

From the docs

base_url accepts both https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/ and https://YOUR-RESOURCE-NAME.services.ai.azure.com/openai/v1/ formats.
learn.microsoft.com/en-us/azure/foundry/openai/api-version-lifecycle

Anthropic-compatible API

Supported

Claude models only. This endpoint gives native Messages API access to Anthropic's Claude models; it does not put other model families behind the Anthropic format.

ANTHROPIC_BASE_URL
https://<resource name>.services.ai.azure.com/anthropic
Auth
x-api-key: $AZURE_API_KEY, or Authorization: Bearer <Microsoft Entra ID token> (scope https://ai.azure.com/.default)
Notes
Serves Anthropic's Claude models deployed in Foundry (Messages and Token Count APIs) via the Anthropic SDK (AnthropicFoundry client); not a translation layer for other model families. model is the deployment name. Some Claude Mythos models support Entra ID only.

From the docs

Your base URL, which is of the form https://<resource name>.services.ai.azure.com/anthropic.
learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/use-foundry-models-claude

Documented limitations

Parameters, content types and features Microsoft Foundry / Azure OpenAI's docs say its compatibility layers ignore, reject or change, each with the line it comes from. A layer with nothing listed may still differ in ways the docs do not spell out.

OpenAI-compatible layer1

Anthropic-compatible layer1

Example from Microsoft Foundry / Azure OpenAI's docs

Copied verbatim from the provider's documentation, placeholders included.

Provider example
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),
    base_url="https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/"
)

response = client.responses.create(
  model="gpt-4.1-nano", # Replace with your model deployment name
  input="This is a test.",
)

More on Microsoft Foundry / Azure OpenAI

Newsletter

Know when a provider changes its API

One email per week. New models, new endpoints and the compatibility changes that break a base URL, and what they mean for your stack.