Exa page contents

Retrieve the readable text of up to 10 web pages by URL, with optional query-focused highlights. Exa serves from its crawl cache when the page is fresh enough and live-crawls otherwise, so this answers for pages a plain fetch would be blocked from. Returns per-URL status so a page that could not be read is named rather than silently missing.

TRY IN PLAYGROUND →

Input

Example output

{
  "source": "exa",
  "fetchedAt": "2026-09-13T20:00:00.000Z",
  "count": 1,
  "results": [
    {
      "title": "What is the x402 payment protocol?",
      "url": "https://example.com/x402-explained",
      "publishedDate": "2026-08-02T00:00:00.000Z",
      "author": null,
      "text": "x402 is an HTTP-native payment protocol ..."
    }
  ],
  "statuses": [
    {
      "id": "https://example.com/x402-explained",
      "status": "success"
    }
  ]
}

Try it - see the 402 challenge (free)

curl -i -X POST https://agent402.tools/api/exa-contents \
  -H "Content-Type: application/json" \
  -d '{"urls":["https://example.com/x402-explained"]}'

The response is HTTP 402 Payment Required with exact payment requirements. Any x402 v2 client pays automatically and retries:

Paid call (JavaScript agent)

import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";
import { metaTitle, metaDescription } from "./seo-meta.js";

const client = new x402Client();
registerExactEvmScheme(client, { signer: privateKeyToAccount(KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);

const res = await payFetch("https://agent402.tools/api/exa-contents", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    "urls": [
      "https://example.com/x402-explained"
    ]
  }),
});

Related tools