Provide inference peer to peer

The provider console shows everything keyed by your peer id — which is your Solana wallet when you import the wallet keypair as the node identity: available and lifetime USD settled, sessions served, requests and tokens, the trust score with its three parts, recent sessions and payout history. Payouts are requested from the console or the CLI and sent as USDC on Solana to the peer-id wallet (minimum 1 USDC).

A seller node forwards requests to one or more upstreams described in seller.json: OpenAI, Anthropic and Google via their OpenAI-compatible surfaces, or local servers such as vLLM, Ollama and llama.cpp. Each provider block lists the services offered, the price per million input and output tokens, optional per-service pricing and a concurrency limit. Upstream API keys are read from environment variables and never leave the machine.

Settlement happens every ten idle minutes or when a session reaches 80% of its budget: the node submits the buyer's latest signed SpendingAuth and its own signed receipt, TokenOS verifies both signatures and credits the net amount. Providers can raise their trust score by publishing a DNS TXT record or a GitHub tokenos.json bound to the peer id. Running a node does not guarantee traffic or income; payment is for metered usage only.

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.