What an Anthropic-compatible API is

Anthropic-compatible means an endpoint speaks the Messages API that Claude Code and the Anthropic SDKs use. Point them at it with a base URL and an auth token, and they drive a non-Claude model through it.

The Messages format

The Anthropic dialect differs from OpenAI’s: a top-level system, a required max_tokens, and a content-block response shape. Redline exposes this at https://redline-gateway.pages.dev/v1/messages, translating to whichever model you name so an Anthropic client can drive it.

The base URL has no /v1

Clients append /v1/messages themselves, so the base URL is https://redline-gateway.pages.dev with no path. The key goes in ANTHROPIC_AUTH_TOKEN (a bearer header) for Claude Code, or auth_token / authToken in the SDKs.

One caveat

Not an Anthropic-backed setup Anthropic does not officially support routing Claude Code to non-Claude models through a gateway. This works because Redline translates the Messages API, and the model must support tool calling for the agent to act. See the Claude Code guide.

Guides: Claude Code, Anthropic SDK (Python), Anthropic SDK (TS).

Related

OpenAI-compatible APIAn OpenAI-compatible API accepts the same requests as OpenAI’s chat completions endpoint, so any OpenAI SDK works by changing the base URL. LLM gatewayAn LLM gateway is one API in front of many model providers, adding keys, billing, spend limits and logging without changing your code. Red-teaming LLMsRed-teaming an LLM means attacking your own model on purpose: jailbreaks, prompt injection and abuse generation, to find failures before an attacker does.

All concepts · Integration guides · Browse models