# Inferit

> Inferit is a two-sided marketplace for LLM inference. Buyers call one OpenAI-compatible API; sellers list
> open-weight models they host. Every request is routed to the cheapest healthy offer and settled in batches through
> a bounded-custody escrow on Whitechain. Prices are all-in (seller price plus a 5% platform fee).

## Testnet demo

This deployment runs on Whitechain Sepolia (chain id 1874), a test network. Buyers fund the escrow with
Inferit Test Credit (ITC), a faucet-only test token with no monetary value: it is not a stablecoin, cannot be
redeemed and is not money. Prices are quoted in test dollar units (1 ITC = 1 unit). Some offers may be demo
sellers that return canned (mock) completions; they say so in their replies. Do not send sensitive data. Every API response
carries `x-inferit-network: whitechain-sepolia` and `x-inferit-testnet: 1`.

## Settlement network

- Network: Whitechain Sepolia (`whitechain-sepolia`), chain id 1874, testnet
- Escrow (MarketEscrow): 0x705dD9eCffa888FbcF2849eAE2D3b136eb78B7e0
- Token: 0x2E672dFE33EA977FD064E01aDe7d8c73B3Be7fBB (ITC, 6 decimals, faucet-only, no value)
- Explorer: https://explorer.testnet.whitechain.io (escrow: https://explorer.testnet.whitechain.io/address/0x705dD9eCffa888FbcF2849eAE2D3b136eb78B7e0)
- Gas faucet (native WBT): https://faucet.testnet.whitechain.io
- Test token faucet: call `faucet()` on the token contract (1,000 ITC per address per 24 h)
- Settlement is final only once the batch is finalized on-chain (OP Stack): usage rows report `finality`
  'pending' until then. GET https://api-production-c74b9.up.railway.app/v1/rails has the live rail details and health.

## Live models

- qwen/qwen-2.5-14b-instruct: from 0.084000 / 0.168000 per 1M input / output tokens (all-in, 16% under list)

## Use it

- Base URL: https://api-production-c74b9.up.railway.app/v1 (OpenAI-compatible). Authenticate with `Authorization: Bearer ik_...`.
- Chat: POST https://api-production-c74b9.up.railway.app/v1/chat/completions (streaming supported).
- Minimum discount vs list price: POST https://api-production-c74b9.up.railway.app/min{N}/v1/chat/completions, or header `x-min-discount: N`.
- Models and prices: GET https://api-production-c74b9.up.railway.app/v1/models (list price in `pricing`, best live price in `best_price`).

## Agents: pay per request with x402 (no account, no API key, no native gas)

- POST https://api-production-c74b9.up.railway.app/v1/chat/completions (or /min{N}/v1/chat/completions) with NO Authorization header answers
  402 Payment Required, x402 v2: header PAYMENT-REQUIRED (base64 JSON) and the same PaymentRequired JSON as the body.
  One requirement: scheme `exact`, network `eip155:1874`, asset 0x2E672dFE33EA977FD064E01aDe7d8c73B3Be7fBB (6 decimals), payTo
  0x705dD9eCffa888FbcF2849eAE2D3b136eb78B7e0 (the escrow, not Inferit), amount = this request's worst-case all-in cost (at least
  10000 base units = 0.010000 ITC), maxTimeoutSeconds 120, extra
  {"name":"Inferit Test Credit","version":"1"} (the token's EIP-712 domain; EIP-3009 TransferWithAuthorization).
- Pay with the official client, unmodified: `wrapFetchWithPayment(fetch, client)` from @x402/fetch, with
  `client = new x402Client().register('eip155:*', new ExactEvmScheme(account))` (ExactEvmScheme from
  @x402/evm/exact/client, account from viem). Recent x402Client versions (with spend controls, e.g. 2.28) only pay
  assets they know by default, so allow this one (older 2.x clients need nothing):
  `client.setSpendControls({ allowedAssets: [{ network: 'eip155:1874', asset: '0x2E672dFE33EA977FD064E01aDe7d8c73B3Be7fBB', maxAmountPerPayment: '1000000' }] })`.
- The paid retry carries PAYMENT-SIGNATURE. The server verifies it, deposits it INTO the escrow as YOUR balance
  (MarketEscrow depositWithAuthorization: bounded custody), then serves and charges the request like any other
  (streaming supported). The response carries PAYMENT-RESPONSE (base64 SettleResponse: transaction, network, payer)
  and x-inferit-buyer-cost-micro. Usage is settled on-chain in batches (LineSettled), like API-key usage.
- What the request does not use stays your escrow balance: spend it later with an API key (next section) or
  withdraw it from the escrow (requestWithdraw, then executeWithdraw after the delay; needs native gas). If a paid
  request fails after the payment was credited, the error says so and the credit is still yours.
- The server pays the gas of every payment. Test tokens without gas: POST https://api-production-c74b9.up.railway.app/v1/faucet {"address":"0x..."} mints 1,000 ITC
  to that address (once per 24 h per address; the server pays the gas).
- Machine-readable: GET https://api-production-c74b9.up.railway.app/.well-known/x402.

## Agents: API key (sign in with the wallet, no gas)

1. POST https://api-production-c74b9.up.railway.app/v1/auth/evm/challenge {"address":"0x..."} -> {"message", "nonce", "expiresAt"}
2. Sign `message` with the wallet (EIP-191 personal_sign), then POST https://api-production-c74b9.up.railway.app/v1/auth/evm/verify
   {"message","signature"} -> {"token"} (a session token, ise_...).
3. POST https://api-production-c74b9.up.railway.app/v1/keys with Authorization: Bearer <session token>, body {"name":"my-agent"} -> {"key":"ik_..."}
   (shown once; optional spendLimitMicro and minDiscountPct).
4. Call the API with Authorization: Bearer ik_... It spends your escrow balance on the whitechain-sepolia rail: x402
   payments credit it, or deposit yourself with depositAndSetCap on the escrow (needs native gas).

## Marketplace data (aggregated, no seller identities)

- GET https://api-production-c74b9.up.railway.app/api/marketplace
- GET https://api-production-c74b9.up.railway.app/api/markets/{model}
- GET https://api-production-c74b9.up.railway.app/api/stats
- GET https://api-production-c74b9.up.railway.app/v1/rails
- GET https://api-production-c74b9.up.railway.app/health, GET https://api-production-c74b9.up.railway.app/metrics (settlement backlog, finality lag, operator gas runway)

## Response headers

x-request-id, x-inferit-attempts, x-inferit-buyer-cost-micro (an HTTP trailer on streams), x-inferit-offer
(opaque), x-inferit-rail, x-inferit-network, x-inferit-testnet (1 on any network but mainnet). Money is integer
micro-units (1e-6 of a dollar unit; on testnets, of an ITC); prices are micro-units per 1M tokens.

## Errors

OpenAI-shaped {"error":{"message","type","code"}}: 402 insufficient_funds, 404 model_not_found,
503 no_available_offers (with retry-after). Without credentials, 402 is the x402 challenge (body = the x402
PaymentRequired JSON); a refused payment answers 402 again with the reason in `error`; 503 x402_settlement_pending /
x402_unavailable say whether anything was charged.