FreeIA Gateway aggregates 10 free LLMs (9 cloud + Ollama) behind an OpenAI and Anthropic-compatible API. Automatic fallback, smart cache, native MCP server. No subscription.
Nine providers aggregated, one endpoint, zero cost.
Cerebras → Groq → Sambanova → Gemini → HuggingFace → NVIDIA NIM → Cloudflare AI → OpenRouter → Mistral → Ollama. 429 error or outage? The next one silently takes over.
Endpoint /v1/chat/completions compatible OpenAI. Fonctionne avec tout client compatible : AnythingLLM, OpenCode, LibreChat, Continue.dev, Jan, LM Studio, Cursor…
If a provider goes down or saturates, automatic cooldown (30s). Silent retry. Zero manual intervention.
SQLite tracking of requests and tokens per provider. Automatic daily reset. You never exceed free tier limits.
Upload your docs, query them with your free LLMs. No cloud subscription required.
Nothing passes through our servers. Only requests to the free public APIs leave your network.
Connect Claude Code, Cursor or Cline directly to your free LLMs. MCP-compatible HTTP endpoint. 3-line config.
Long context → Cerebras skipped automatically. Image detected → Gemini only. Explicit provider hint → direct routing. Zero added latency.
Exact cache (SHA-256) or semantic (fastembed, cosine ≥ 0.90). Similar requests served from SQLite (TTL 1h). Preserves your quotas.
Point the Anthropic SDK at http://localhost:8002. Native /v1/messages endpoint — same format, same fields, free LLMs behind. stream=False only (streaming not supported).
Create an account on each platform and generate your API key. No credit card required on any of them.
10 minutes, no experience required. If you can copy-paste, you can do this.
git clone over the ZIP option in step 1. On Mac/Linux: already included.Two options. The easiest: download the ZIP, unzip it, no Git needed.
With the ZIP: right-click the downloaded file → Extract All → you get a freeiaforge-master folder. Rename it to freeiaforge if you want, then open it.
One key is enough to start. Easiest: Cerebras — Google login, no credit card, 5000 requests/day.
csk-…) — keep it handy for the next step.You can add more keys later to increase your quota: Groq, Gemini, Mistral, OpenRouter… All optional.
One command. The script creates the config file, lets you paste your key, then starts everything.
start.bat in the freeiaforge folder, OR in the terminal:.\start.bat
./start.sh
What happens?
backend/.env and asks you to paste your key.backend/.env in Notepad (or your editor), find the CEREBRAS_API_KEY= line, paste your key after the =, save, close.Uvicorn running on http://0.0.0.0:8002, you're ready.In any OpenAI-compatible client (AnythingLLM, OpenCode, LibreChat, Cursor, Jan, LM Studio…), set these 3 values:
Base URL : http://localhost:8002/v1 API Key : freeai Model : freeai-gateway
Test directly in the browser: http://localhost:8002/docs (interactive Swagger UI).
Docker Desktop is not installed or not running. Install it, open the app, wait until the whale shows "Running", then retry.
Install Git for Windows from git-scm.com. Close and reopen PowerShell after installation.
You ran docker compose up directly instead of the .\start.bat script. Fix: type copy backend\.env.example backend\.env then retry.
Easiest fix: use start.bat instead (double-click or .\start.bat) — no Windows block. Or in PowerShell: Set-ExecutionPolicy -Scope CurrentUser RemoteSigned, confirm with Y, then retry.
Another app is already using that port. Close it, or edit docker-compose.yml and change "8002:8002" to "8003:8002" (then use localhost:8003).
Open source code, no sign-up, no subscription. Your data never passes through our servers — only through the APIs of the providers you choose.