Become a Hoster

Share your GPU with the world — or just your team. Create a free plan to share privately, or set up paid subscriptions and keep 80% of revenue.

Requirements

• A GPU server with at least 4GB VRAM (or a CPU with 8GB+ RAM)
• A publicly reachable endpoint (not localhost or private IPs)
• An OpenAI-compatible server (setup guide)
• An invite code — register to request one

One-command setup

The fastest way to get started. The setup wizard detects your GPU, picks a model, configures Docker Compose, and registers with LLMFinder:

curl -O https://llmfinder.net/llmfinder-hoster.py && python3 llmfinder-hoster.pyCopy

The wizard:

• Detects your GPU and available VRAM
• Downloads the right model into ~/llmfinder-models/
• Calculates optimal context size from GGUF metadata + VRAM
• Generates a docker-compose.yml with your backend (llama.cpp, Ollama, or vLLM) plus a Cloudflare tunnel for public access
• Registers your endpoint with LLMFinder and runs a verification test

Top-level menu (7 options): 1) Setup wizard, 2) Add/update models, 3) Server verification test, 4) Update server URL, 5) Rotate bearer token, 6) Uninstall, 7) Exit.

Manual registration

If you already have a server running, register it directly:

curl -X POST https://api.llmfinder.net/hosters/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "My GPU Server",
    "email": "[email protected]",
    "endpoint_url": "https://my-server.example.com",
    "api_key": "my-bearer-token",
    "invite_code": "BETA2026",
    "models": [
      {
        "model_id": "llama-3-8b",
        "model_alias": "Llama 3 8B",
        "price_per_input_token": 100,
        "price_per_output_token": 300,
        "context_window": 8192,
        "max_tokens": 2048
      }
    ]
  }'Copy

Supported server software

Blocked endpoints

The following cannot be registered (ToS violation):

• Localhost or private IPs (127.x, 10.x, 192.168.x) — must be publicly reachable
• Commercial API providers (OpenAI, Anthropic, Google, etc.)
• Commercial model IDs (gpt-4, claude-*, gemini-*)

Verification

After registration, LLMFinder runs two checks:

1. Health check — GET /health must return HTTP 200
2. Inference test — sends a test prompt, expects a valid response

Once both pass, your server goes live and starts receiving traffic.