Prefetch

Web scraping API, clean markdown from any URL

Turn any page into clean markdown or JSON, ready for your LLM.

Get API Key
Try these brands
No Credit Card
Free to start
Free Plan
1,000 pages/mo

From a page of markup to clean context.

Scrape isolates a page's content as clean markdown, so you spend tokens on the page, not the wrapper.

  1. Markdown, not markup

    Navigation, footers and cookie bars are stripped, and every link made absolute.

  2. JSON in your own schema

    Describe the fields in a prompt or a JSON Schema, and anything missing comes back null.

  3. Rendered, unblocked, checked

    Real browsers, stealth and proxy tiers, and an optional prompt-injection check.

page.html

<div class="nav__item js-hover" data-t="…">

<script async src="/v3/bundle.8f2c.js"></script>

<span class="sr-only cookie-banner__x">

<h1 class="hero__title t-48">Financial…

page.md

# Financial infrastructure to grow your revenue

Join the millions of companies that use Stripe to accept payments online and in person.

- Payments
- Billing
- Connect

[Pricing](https://stripe.com/pricing)

markdown.char_count 4,821word_count 702

Scrape pages with Claude

Ask for any page as clean markdown, or send the same request with your API key.

# claude.ai/directory/prefetch → Connect
# Sign in to Prefetch, Allow access. No key to paste.
# Claude Code on the same Claude account has it too.

# Then just ask:

  Use prefetch_scrape on stripe.com/pricing and turn
  the plans into a comparison table.
Open in Claude

What teams build with the Scrape API

  • RAG & agent context

    Feed retrieval pipelines and agents markdown that is already clean, instead of HTML that costs many times the tokens.

  • Structured extraction

    Pull prices, specs, job details or contacts out of any page as JSON that matches your schema.

  • Competitive research

    Read competitors' pricing, docs and changelogs as clean text you can diff, summarise or search.

  • Documents & PDFs

    Point it at a PDF and get its text back as markdown, up to 300 pages, through the same call.

1 credit per page

Summaries, JSON extraction and the prompt-injection check add 3 credits a page, charged once however many of them you ask for. Every plan unlocks every endpoint, failed requests are free, and requests pause at your limit rather than billing past it.

Free

$0

USD

/month

1,000 credits / month

Start Free
  • Up to 1,000 pages
  • 1 concurrent request
  • 30 requests per minute
  • No credit card required

Starter

$9

USD

/month

5,000 credits / month

Get Starter
  • Up to 5,000 pages
  • 10 concurrent requests
  • Unlimited requests per minute
  • Email support
  • $5 per 2,500 additional credits

The same plan unlocks every other endpoint too. Each line is the whole month of 5,000 credits spent there instead of on pages. Mix them however you like.

  • 5,000 name lookups: Company Name to Domain API

    (1 credit per lookup, a company, brand or product name in, its official website's domain out)

  • 5,000 site maps: Sitemap API

    (1 credit per call, every URL a site exposes, from its sitemaps and links, without fetching a page)

  • 5,000 crawled pages: Web Crawling API

    (1 credit per page, a whole site, or one section of it, rendered page by page into clean markdown)

  • 5,000 screenshots: Screenshot API

    (1 credit per call, any URL to a hosted image, at any viewport, full page or above the fold)

  • 5,000 page checks: Website Monitoring API

    (1 credit per page checked, pages re-checked on your schedule, with a webhook carrying only what changed)

  • 1,000 company lookups: Company Data API

    (5 credits per call, the legal entity, its size, founding year and published contacts behind a domain)

  • 1,000 classifications: Website Classification API

    (5 credits per call, the IAB category, subcategory and a readable description of any URL)

  • 500 brand lookups: Brand API

    (10 credits per call, logos, colors, fonts and social assets pulled from any domain)

  • 500 answers: Web Research API

    (10 credits per answer, a research question in, a sourced answer in your own JSON shape out)

  • 416 enrichments: Company Enrichment API

    (12 credits per call, brand, company and classification for any domain, from one page load)

Failed requests are never charged. Top-up credits are spent after your monthly credits and never expire.

Web Scraping API questions

Scale with confidence. Handle thousands of requests per second on fast, reliable infrastructure.

Registered Users
300+
API calls processed
40k
Uptime
99.9%

Ready to get started?

Create an account instantly, or contact us to design a custom package for your business.

Start now Book a call

Up in 5 minutes

Make your first API call in under 5 minutes. No setup headaches, just copy, paste, ship.

Quick start guide

API reference

Request schemas, response examples, everything you need to integrate.

Browse the docs