dev.fun Inference

New

by dev.fun Inference

Keyless AI inference with per-call USDC payments on Monad.

Infrastructure

Endpoints · 3

Base URLhttps://inference.dev.fun
POST/api/x402/v1/chat/completions$0.001variesOpenAI-compatible chat completion. USD 0.001 per delivered request plus the model's token usage, quoted fresh for each request; pay with the exact or upto scheme.
GET/api/x402/v1/modelsFreeThe models you can call, with the token rates of each model and the fixed fee per request.
POST/api/x402/v1/payments/statusFreeThe settlement status of a signed payment, without running the model again. Send the original PAYMENT-SIGNATURE header and an empty JSON body.

Call the provider directly and settle x402 per request.

Quickstart · x402 flow

1 · Call without payment. The service replies 402

bash
curl -i https://inference.dev.fun/api/x402/v1/chat/completions \  -H "Content-Type: application/json" \  -d '{"model": "qwen/qwen-2.5-7b-instruct", "messages": [{"role": "user", "content": "say ok"}], "max_tokens": 50}'
Response
HTTP/1.1 402 Payment Required{ "x402Version": 2,  "accepts": [{ "scheme": "exact", "network": "eip155:143",  "asset": "USDC", "maxAmountRequired": "0.001" }] }

2 · Sign the payment with your agent wallet and retry

bash
curl https://inference.dev.fun/api/x402/v1/chat/completions \  -H "X-PAYMENT: <base64 payment payload signed by your EOA>" \  -H "Content-Type: application/json" \  -d '{"model": "qwen/qwen-2.5-7b-instruct", "messages": [{"role": "user", "content": "say ok"}], "max_tokens": 50}'
Response
HTTP/1.1 200 OK

Any EOA on Monad can pay.

Any APIs or tools listed are provided for discovery purposes only and do not constitute an endorsement or recommendation by the Monad Foundation.