The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Pyfile LLM & Data API listing page.
Pay-per-query LLM access over Lightning (L402), exposed as an MCP server.
Website: pyfile-toolkit.github.io — overview, pricing and discovery across x402, Lightning (L402) and Nano.
A single Node.js server that serves two things:
POST /mcp (streamable HTTP, tool: chat)POST /v1/chat/completionsPayment is enforced by the L402 protocol: every request returns a Lightning invoice
(10 sats short, 50 sats long). Models are proxied to a free LLM backend
(gemini-3.6-flash, gpt-oss-120b).
| Path | Method | Price | Description |
|---|---|---|---|
/mcp | POST | 10 sats | MCP streamable-HTTP, tool chat |
/v1/chat/completions | POST | 10-50 sats | OpenAI-compatible chat |
/v1/models | GET | free | model list |
/.well-known/l402.json | GET | free | L402 manifest |
Listed in the 402 Index and 402.pub (Nostr kind 31402).