Ask a web page a question, with verified quotes API
AI question answering over one live web page or document URL: an answer drawn only from the page text, verbatim quotes with character offsets checked against the page, an answerable flag and low/medium/high confidence. answerable:false (page lacks the answer) is a normal, charged 200 result. Without a question: summary, key points, title. Also final URL, page size, truncation flag. Generated by Anthropic Claude under a fixed Kit Rx prompt; may miss or misstate details.
$0.004 per call USDC over x402 v2 on Base, Avalanche or Sei. No signup, no API key. Requests that fail or match nothing are not charged.
Endpoint
GET https://web.kit-rx.com/v1/web/read
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
url | string | yes | http or https URL of a public page (HTML, or a PDF/DOCX/XLSX document; a bare domain is fetched as https://). Default ports only; credentials, IP addresses, localhost and private or single-label names are rejected. e.g. https://www.archives.gov/founding-docs/declaration-transcript |
q | string | no | Question to answer from the page, up to 500 characters. Omit it for a summary. e.g. From what do governments derive their just powers, according to this document? |
mode | string: answer, summary | no | answer (default when q is given: answer, verbatim quotes with offsets, answerable flag, confidence) or summary (default without q: summary, key points, title). e.g. answer |
max_chars | integer | no | Characters of the page's main content (as Markdown) read, 1000 to 30000. Default 30000. Longer pages are cut and flagged truncated. e.g. 30000 |
Example request
https://web.kit-rx.com/v1/web/read?url=https%3A%2F%2Fwww.archives.gov%2Ffounding-docs%2Fdeclaration-transcript&q=From+what+do+governments+derive+their+just+powers%2C+according+to+this+document%3F
Without payment the server answers 402 Payment Required with the price (4000 atomic USDC) in the PAYMENT-REQUIRED header. Any x402 v2 client pays and retries automatically. A request with no parameters runs this example.
curl -i "https://web.kit-rx.com/v1/web/read?url=https%3A%2F%2Fwww.archives.gov%2Ffounding-docs%2Fdeclaration-transcript&q=From+what+do+governments+derive+their+just+powers%2C+according+to+this+document%3F"
Pay from an agent
AgentCash: fetch the URL. OpenDexter MCP: x402_fetch. Kit Rx MCP server: https://api.kit-rx.com/mcp. Code:
import { x402Client } from "@x402/core/client";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { wrapFetchWithPayment } from "@x402/fetch";
import { privateKeyToAccount } from "viem/accounts";
const client = new x402Client();
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.BUYER_KEY) });
const pay = wrapFetchWithPayment(fetch, client);
const res = await pay("https://web.kit-rx.com/v1/web/read?url=https%3A%2F%2Fwww.archives.gov%2Ffounding-docs%2Fdeclaration-transcript&q=From+what+do+governments+derive+their+just+powers%2C+according+to+this+document%3F");
console.log(await res.json());
Example response
{
"query": {
"url": "https://www.archives.gov/founding-docs/declaration-transcript",
"q": "From what do governments derive their just powers, according to this document?",
"mode": "answer",
"max_chars": 30000
},
"result": {
"mode": "answer",
"answerable": true,
"answer": "According to the page, governments derive their just powers from the consent of the governed.",
"quotes": [
{
"text": "Governments are instituted among Men, deriving their just powers from the consent of the governed",
"char_start": 1305,
"char_end": 1402
}
],
"quotes_dropped": 0,
"confidence": "high",
"title": "Declaration of Independence: A Transcription | National Archives",
"title_source": "page",
"final_url": "https://www.archives.gov/founding-docs/declaration-transcript",
"page_chars": 9990,
"page_chars_read": 9990,
"truncated": false,
"model_family": "Claude",
"ai_generated": true
},
"sources": [
{
"name": "Cloudflare DNS over HTTPS (JSON API)",
"url": "https://developers.cloudflare.com/1.1.1.1/encryption/dns-over-https/make-api-requests/dns-json/"
},
{
"name": "Cloudflare Workers AI toMarkdown",
"url": "https://developers.cloudflare.com/workers-ai/features/markdown-conversion/"
},
{
"name": "Anthropic Claude (AI-generated text)",
"url": "https://www.anthropic.com/claude"
},
{
"name": "Live HTTP(S) fetch of the URL",
"url": "https://www.archives.gov/founding-docs/declaration-transcript"
}
],
"notes": [
"AI-generated answer by Anthropic Claude under a fixed Kit Rx prompt, based only on the fetched page text; it can misread or miss details. Quotes are checked in code to be exact substrings of the page text; the answer itself is not verified.",
"Quote char_start and char_end are 0-based, end-exclusive UTF-16 offsets into the page text as extracted at fetch time (Markdown of the main content, as web.markdown returns it).",
"Page fetched live by the Kit Rx fetcher (User-Agent KitRx/1.0) and converted with Cloudflare Workers AI toMarkdown; content belongs to its publisher."
],
"attribution": [
"DNS resolved via Cloudflare 1.1.1.1 DNS-over-HTTPS."
],
"generated_at": "2026-11-15T05:52:41.899Z"
}
Kit Rx Website Security Headers and Markdown: Website tools for AI agents: security headers grade, page and document to Markdown, site checks, and AI page reading, extraction, summaries, translation, OCR and cited research briefs, paid per call over x402. Machine-readable: OpenAPI, llms.txt, /.well-known/x402, agent skills.