Prismnetwork · Inference Inference

import { wrapFetchWithPayment } from "@x402/fetch";
import { privateKeyToAccount } from "viem/accounts";

const account = privateKeyToAccount(process.env.PRIVATE_KEY);
const fetchWithPay = wrapFetchWithPayment(fetch, account);

const res = await fetchWithPay("https://api.prismnetwork.tech/inference/v1/inference", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    "model": "llama3.2:3b",
    "options": {
      "num_predict": 64
    },
    "prompt": "Explain metered GPU compute in one sentence."
  }),
});
const data = await res.json();

curl -X POST \
  "https://api.prismnetwork.tech/inference/v1/inference" \
  -H "Content-Type: application/json" \
  -d '{"model":"llama3.2:3b","options":{"num_predict":64},"prompt":"Explain metered GPU compute in one sentence."}' \
  -H "X-PAYMENT: <signed x402 payment>"

{
  "lease_id": 1047,
  "model": "llama3.2:3b",
  "response": "Metered GPU compute bills by the second and settles onchain.",
  "usage": {
    "completion_tokens": 14,
    "duration_ms": 640,
    "prompt_tokens": 12
  }
}