Agent Fetch Hub

URL in, clean Markdown out. Every call is paid inside the request over x402. No signup, no API key, no dashboard.

Endpoints

RoutePriceWhat it does
POST /extract 0.001 USDC Fetch one URL and return clean article Markdown without navigation, ads or cookie banners.
POST /metadata 0.002 USDC Return title, description, OpenGraph card, canonical URL, feeds, favicon and detected technologies for one URL.
POST /structured 0.005 USDC Fill a caller supplied JSON Schema from one web page and report source and confidence for every field.
POST /diff 0.003 USDC
0.001 USDC for a baseline call		 Compare a page against its last stored state, or two supplied documents, and report only the content changes.
POST /batch/extract 0.008 USDC Extract up to ten URLs in one paid call.
POST /product 0.005 USDC Return the structured offer of one product page: identifiers, price, availability, shipping, variants, ratings, images and seller, each with its source.

How a call works

curl -s -X POST https://fetch.halowerk.com/extract \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com/article","format":"markdown"}'

The first call answers with HTTP 402 and the accepted payment terms. An x402 capable client signs the terms and repeats the request; the answer arrives in the same round trip. Any x402 client library, or an MCP client pointed at /mcp, handles this without further setup.

Rules we follow

  • robots.txt of the target origin is respected. A disallowed path is refused and never charged.
  • Paywalls and bot walls are not bypassed.
  • Cached copies expire after at most 24 hours, product answers after 30 minutes.
  • Product prices are parsed, never calculated or converted. Every field names its source and raw value.
  • Private and link local address ranges are refused.
  • A failed extraction is rejected before settlement.

Discovery

Operational figures

Rolling 30 day window, updated live: 12 requests, 9 of them paid, 9 settlements, 0.027 USDC volume, 0 documents in cache.