Buy inference peer to peer

The buyer console issues tos_ API keys bound to your Solana wallet. Each key can carry daily, monthly and total spend limits in credits and an expiry; the buyer node uses the key only to reserve credits for a session and to request closure when a seller disappears. Keys are shown once and stored locally as TOKENOS_API_KEY.

Run tokenos-p2p buyer start and point any OpenAI SDK at http://127.0.0.1:8377/v1. The node discovers sellers over the DHT and the indexer, picks the cheapest offer for the requested model (ties broken by trust score), opens an encrypted direct connection and funds a session with a default budget of 10 credits. The first session with any new seller is capped at 10 credits. Requests can be pinned to a specific peer with the x-tokenos-pin-peer header.

You pay exactly the seller's price per million tokens, metered from the response's own usage field and converted at $0.10 per credit; the protocol fee is taken from the seller side. The sessions table shows every payment channel the node opened with its settled amount, request count and status; unspent credits return to your balance when a session closes.

About TokenOS

TokenOS is the AI operating system for the autonomous Web3 economy. It combines an agentic IDE that turns a prompt into a deployed dApp, a marketplace of x402-paid AI agents, a peer-to-peer AI inference market where anyone can sell spare API quota or GPU time for USDC, MCP and A2A connectors for Claude, Cursor and ChatGPT, and the $TOS utility and governance token on Solana.

Builders pay with prepaid credits; sellers and agent creators are paid for work actually delivered; TokenOS indexes, verifies and settles. Nothing on this site is investment advice, and node payouts, agent payments and referral credits are fees for usage — not token distributions or returns.

How TokenOS works

Build: connect a wallet, describe the app you want and choose the chain, network and wallet providers in Live Web3 Config. The build pipeline analyses the request, generates the project, bundles a preview, runs a headless render check and repairs what fails before it hands you a verified preview. Iterate in the update chat with inline diff review, tweak visuals in Design Mode, then deploy contracts, launch a token and go live on TokenOS hosting, Vercel or Netlify.

Agents: publish x402-paid agents from the Agent Builder, let buyers try them for free and pay per call in USDC, expose them to Claude, Cursor and ChatGPT through the MCP server and to other agents through A2A agent cards, and run them on a schedule as Autopilots with an approvals inbox.

Inference: the P2P AI network lets anyone sell spare API quota or a local model to buyers who pay with prepaid credits. Sessions are encrypted end to end, the seller signs receipts for every token delivered, TokenOS verifies and settles them and pays providers in USDC on Solana. Everything is priced in credits (1 credit = $0.10 of usage) and documented at /docs.