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

API compatibility - 10 documented limits

Anthropic (Claude API) API compatibility

Anthropic's native Messages API is at https://api.anthropic.com, the default ANTHROPIC_BASE_URL. Anthropic also documents an OpenAI SDK layer at https://api.anthropic.com/v1/ (chat/completions). The docs list 10 limitations: 10 for the OpenAI-compatible layer.

Verified against Anthropic'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

Not for production. Anthropic describes this layer as a way to test and compare model capabilities, not a long-term or production-ready solution for most use cases.

Base URL
https://api.anthropic.com/v1/
Endpoints
  • chat/completions
Auth
Claude API key as the OpenAI client's api_key (sent as Authorization: Bearer); multi-workspace personal/service account keys also need the anthropic-workspace-id header
Notes
Anthropic positions this layer for testing and comparing model capabilities, not as a long-term or production-ready solution for most use cases. The docs describe Chat Completions only. Thinking is enabled via extra_body but the OpenAI SDK does not return Claude's thinking. Most unsupported fields are silently ignored.

From the docs

This compatibility layer is primarily intended to test and compare model capabilities, and is not considered a long-term or production-ready solution for most use cases.
platform.claude.com/docs/en/cli-sdks-libraries/libraries/openai-sdk

Anthropic-compatible API

Native API
ANTHROPIC_BASE_URL
https://api.anthropic.com
Auth
Authorization: Bearer <API key or short-lived token>, or legacy x-api-key; anthropic-version header required
Notes
This is the native Messages API that the other providers' Anthropic-compatible layers imitate; https://api.anthropic.com is the default ANTHROPIC_BASE_URL.

From the docs

The Claude API is a RESTful API at https://api.anthropic.com that provides programmatic access to Claude models and Claude Managed Agents.
platform.claude.com/docs/en/api/overview

Documented limitations

Parameters, content types and features Anthropic (Claude API)'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 layer10

Anthropic-compatible layer0

No limitations listed in the docs read.

Example from Anthropic (Claude API)'s docs

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

Provider example
import os

from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("ANTHROPIC_API_KEY"),  # Your Claude API key
    base_url="https://api.anthropic.com/v1/",  # the Claude API endpoint
)

response = client.chat.completions.create(
    model="claude-opus-5-5",  # Claude model name
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Who are you?"},
    ],
)

More on Anthropic (Claude API)

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.