The Anthropic Messages format on any model
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. Wild West API exposes this at https://wildwestapi.com/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://wildwestapi.com 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 Wild West API 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).