Structured Data Extraction (AI)

Extract structured JSON from a web page or text with fields you define: send url (or text) and fields like {"price": "price in EUR as number", "in_stock": {"type": "boolean"}}, get back exactly those fields, typed and validated against a JSON schema. Types: string, number, integer, boolean, string[], number[]. Fields the content does not state come back as null instead of being guessed. Up to 25 fields; optional instructions for extra rules. For product data, prices, contact and company details, job postings, event data, specs. Uses Claude Haiku 5.5 with structured outputs; page content is treated as data, instructions inside it are ignored. Not charged when the page cannot be read.

Call it

import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client();
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);

const res = await payFetch("https://agentsvc.io/api/v1/proxy/page-extract", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({"url":"https://www.zalando.de/zalando-impressum/","fields":{"company":"legal company name","city":"city of the registered office","register_number":"commercial register number","vat_id":"VAT ID"}}),
});
const { data, payment } = await res.json();  // payment.status "settling"; header X-Payment-Settle: sync returns payment.transaction

Input

Output

Example response (data)

{
  "source": "https://www.zalando.de/zalando-impressum/",
  "title": "Zalando wohnen",
  "data": {
    "company": "Zalando SE",
    "city": "Berlin",
    "register_number": "HRB 158855 B",
    "vat_id": "DE 260543043"
  },
  "fields_filled": 4,
  "fields_total": 4,
  "input_truncated": false,
  "model": "claude-haiku-5-5",
  "extracted_at": "2026-10-10T09:58:24.270Z"
}