free-claude-code vs freellmapi
Provider-backed proxy that runs Claude Code, Codex or Pi on 25 cloud and local providers — fcc-* launchers, local Admin UI with validation, per-tier model routing, IDE/Discord/Telegram hookups. — versus — OpenAI-compatible proxy that stacks free tiers of 18 LLM providers (~1.7B tokens/mo) behind one /v1 — smart routing, failover, per-key quota tracking; Claude Code and Codex shims included.
Same slot — run coding CLIs on non-Anthropic providers for free — different philosophy: FCC is launcher + Admin UI where you pick and validate one provider (with per-tier overrides); FreeLLMAPI stacks 18 providers' free tiers behind a router with automatic failover and quota tracking.
| free-claude-code | freellmapi | |
|---|---|---|
| Stars | 40k | 16k |
| Forks | 6.6k | 2.4k |
| Language | Python | TypeScript |
| License | MIT | MIT |
| Last activity | today | yesterday |
| Topics | gateway | gateway |
| Curated connections | 2 | 3 |
free-claude-code — the curator's take
40k stars because it nails onboarding: one installer, `fcc-server` + `fcc-claude`, paste an NVIDIA NIM key and Claude Code runs for free — the Admin UI validates providers, and the agents' NATIVE /model pickers see the whole FCC catalog. Tier routing is the power feature: send Opus traffic to Kimi, Sonnet to an OpenRouter free route, Haiku to a local LM Studio model. Local models (Ollama, llama.cpp, LM Studio) are first-class. NOT a quota-stacker — you pick a provider rather than multiplex free tiers with failover (that's freellmapi's job), and expect capability drift vs real Anthropic models on complex agentic work. Discord/Telegram remote sessions with voice-note transcription are a genuinely odd, genuinely useful extra.
freellmapi — the curator's take
Use it for personal experimentation when you want real working inference for $0: free tiers stacked across Google/Groq/Cerebras/Mistral/etc., a Thompson-sampling router with 20-attempt failover, and Anthropic Messages + Responses API shims so Claude Code and Codex CLI run straight against the free pool. Also does embeddings, images, TTS, and an MCP server agents can query for live model availability. NOT for production or teams — single-user by design, no billing, and several provider free tiers are ToS-gray (NVIDIA's is eval-only; the repo itself says personal experimentation only). Freemium catch: new models reach free installs 30 days late unless you pay $19/yr for the live catalog.