claude-code-proxy vs freellmapi
LLM routing projects compared
claude-code-proxy translates Anthropic-format requests so clients such as Claude Code can use OpenAI, Gemini, or Anthropic backends. freellmapi is a self-hosted router for free provider tiers and custom OpenAI-compatible endpoints, with model selection, quota tracking, and fallback; it also offers a dashboard and broader client interfaces.
claude-code-proxy: Connect Claude Code to Other Model Providers
A Python proxy that lets Anthropic-compatible clients such as Claude Code use OpenAI, Gemini, or Anthropic backends through LiteLLM. It suits developers who want to route Claude-style requests to another provider.
freellmapi: Route LLM Requests Through One API
FreeLLMAPI is a self-hosted TypeScript router that combines free LLM provider accounts and custom OpenAI-compatible endpoints behind one API. It selects models, tracks quotas, and retries across providers, mainly for personal experimentation and development.
| claude-code-proxy | freellmapi | |
|---|---|---|
| Language | Python | TypeScript |
| License | — | MIT |
| Stars | 3.8k | 30.3k |
| Forks | 494 | 4.2k |
| Last analyzed | Oct 9, 2026 | Oct 3, 2026 |
Key differences
- claude-code-proxy is a Python format-translation proxy, while freellmapi is a TypeScript gateway that routes across configured providers.
- claude-code-proxy focuses on Anthropic-compatible clients and OpenAI, Gemini, or Anthropic backends; freellmapi supports OpenAI-compatible endpoints plus Anthropic, Gemini, and optional Ollama-compatible interfaces.
- claude-code-proxy maps Claude-style haiku and sonnet requests to configurable models; freellmapi selects models and can rotate keys or fall back after rate limits or server errors.
- freellmapi includes a dashboard for keys, routing, a playground, and usage analytics; claude-code-proxy emphasizes proxy configuration and model mappings.
- Both can run in Docker; claude-code-proxy also runs from source with uv, while freellmapi describes desktop installers.
- freellmapi is MIT-licensed and intended for personal experimentation rather than production; claude-code-proxy's provided details describe no comparable usage warning.
Choose claude-code-proxy if you…
- need to keep an Anthropic-compatible client workflow while routing to OpenAI, Gemini, or Anthropic.
- want configurable mappings from Claude-style model requests to OpenAI or Google models.
- prefer a focused Python proxy that supports streaming and non-streaming responses.
Choose freellmapi if you…
- want one API for free provider tiers and custom OpenAI-compatible endpoints.
- need quota tracking, key rotation, fallback, and a dashboard for managing routes and keys.
- are prototyping or experimenting and accept free-tier limits and variability.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.