Back to directory

Anthropic API Proxy for Gemini & OpenAI Models

A proxy server that lets Anthropic clients such as Claude Code send requests to Gemini or OpenAI models, or to Anthropic itself, by translating between the Anthropic API and each provider through LiteLLM.

Anthropic API Proxy for Gemini & OpenAI Models

claude-code-proxy is a proxy server that lets Anthropic API clients, including Claude Code, work against Gemini, OpenAI or Anthropic models by translating requests through LiteLLM. It can be configured to prefer OpenAI, Google or Anthropic as the backend provider, and maps Claude's haiku and sonnet model names to a configurable big and small model on the chosen backend.

Setup requires cloning the repository and providing the relevant API keys, such as an OpenAI key, a Gemini key, or Google Cloud Application Default Credentials with a configured Vertex AI project and region for Gemini access. Anthropic API access is optional and only needed when proxying directly to Anthropic's own models.

It is written in Python and installs its dependencies with uv.

More in LLM gateways

See all 106
  • aihappey-ai

    github.com

    A stateless, multi-provider .NET AI gateway exposing normalized OpenAI- and Anthropic-compatible endpoints, managed agents and skills across a very large catalog of models.

  • Unified AI System

    happy520ai.github.io

    A self-hosted, protocol-first AI gateway and agent control plane for OpenAI, Anthropic, Gemini, MCP and A2A, turning a rough request into a structured, reviewable prompt before it runs.

  • Subroute

    github.com

    A local AI gateway and desktop control desk that gives coding tools one steady endpoint, so switching between AI subscriptions, API providers and local models doesn't mean reconfiguring every client.