Introducing web-scale /monitor - always-on search that pings your agent the moment something comes online. Read the docs →
Web Scraping API - Part of the all-in-one web toolkit
Clean markdown
from any URL.
Turn any URL into clean markdown or structured data for AI agents. Works on the real web: JS-heavy, gated, and region-specific sites.
<!DOCTYPE html><html lang="en" dir="ltr" class="client-nojs vector-feature-langu
age-in-header-enabled vector-feature-toc-pinned-clientpref-1 skin-theme-clientpr
ef-day vector-toc-available"><head><meta charset="UTF-8"><title>NASA - Wikipedia
</title><script>(function(){var ua=navigator.userAgent;var c="client-js";if(/MSI
E|Trident/.test(ua))c+=" ie";document.documentElement.className+=" "+c;})();</sc
ript><meta http-equiv="X-UA-Compatible" content="IE=edge"><link rel="stylesheet"
href="/w/load.php?lang=en&modules=ext.gadget.ReferenceTooltips%7Cext.uls.in
terlanguage%7Cmediawiki.skinning.interface%7Cskins.vector.styles&only=styles
&skin=vector-2022"><meta name="generator" content="MediaWiki 1.41.0-wmf.21">
<meta name="referrer" content="origin"><link rel="preconnect" href="//upload.wik
imedia.org"><link rel="alternate" hreflang="en" href="https://en.wikipedia.org/w
iki/NASA"><link rel="canonical" href="https://en.wikipedia.org/wiki/NASA"></head
><body class="skin-vector skin-vector-search-vue mediawiki ltr sitedir-ltr ns-0
page-NASA rootpage-NASA skin-vector-2022 action-view"><a class="mw-jump-link" hr
ef="#bodyContent">Jump to content</a><div class="mw-page-container"><header clas
s="mw-header" id="mw-header" data-event-name="ui.mw-header"><nav class="vector-h
eader-container" aria-label="Site"><div class="vector-header-start"><a href="/wi
ki/Main_Page" class="mw-logo"><img class="mw-logo-icon" src="/static/images/icon
s/wikipedia.png" alt="" aria-hidden="true" height="50" width="50"><span class="m
w-logo-container skin-invert"><img class="mw-logo-wordmark" alt="Wikipedia" src=
"/static/images/mobile/copyright/wikipedia-wordmark-en.svg" style="width:7.5em">
<img class="mw-logo-tagline" alt="The Free Encyclopedia" src="/static/images/mob
ile/copyright/wikipedia-tagline-en.svg" width="117" height="13"></span></a></div
><div class="vector-header-end"><div id="p-search" role="search"><form action="/
w/index.php" id="searchform" class="cdx-search-input cdx-search-input--has-end-b
utton"><div id="simpleSearch" class="cdx-search-input__input-wrapper"><input typ
e="search" name="search" placeholder="Search Wikipedia" aria-label="Search Wikip
edia" autocapitalize="sentences" title="Search Wikipedia [f]" accesskey="f" id="
searchInput"></div></form></div></div></nav></header></div></body></html><!DOCTY
PE html><html lang="en" dir="ltr" class="client-nojs vector-feature-language-in-
Scraping.
Trusted by 150,000+
companies of all sizes
companies of all sizes
[ 01 / 04 ]
·
Features
//
Full web coverage
//
Scraping that reaches
the whole web
Most scrapers break on JavaScript, login walls, and region locks. Firecrawl handles it all, so every page comes back clean.
Built for LLMs
Clean, AI-ready output.
Firecrawl strips nav, ads, and scripts and returns Markdown, JSON, links, or screenshots in one call.Markdown
Summary
HTML
Links
JSON
Screenshot
Images
Branding
Real browser
JavaScript rendering.
Every scrape runs in real Chromium so React, Vue, and Next.js sites come back complete.https://example.com
Rendering JavaScript...
Speed that feels invisible
Blazingly fast.
P95 latency of 3.4s across millions of pages, built for real-time agents and dynamic apps.URL
Scrape
52 ms
50 ms
51 ms
51 ms
50 ms
50 ms
Docs to data
Document parsing.
Firecrawl can parse and output content from PDFs, DOCX, and more.https://example.com/docs/report.pdf
https://example.com/files/brief.docx
https://example.com/docs/guide.html
docx
Parsing...
Thousands at once
Batch scraping.
Process thousands of URLs in parallel from a single request.https://example.com/changelog
https://example.com/careers
https://example.com/pricing
https://example.com/changelog
Unlock the web
Enhanced mode.
Stealth, geo, proxies, and adaptive retries are on by default so the pages other tools miss come back clean.[ 02 / 04 ]
·
For AI agents
//
For AI agents
//
Built into the AI tools
you already use
Use Firecrawl from 
One command. Connect your agent to Firecrawl via our Skills/CLI or MCP.
npx -y firecrawl-cli@latest init --all --browserAgent onboarding. Are you an AI agent? Fetch this skill to get an API key and start building.
cURL
curl -s https://firecrawl.dev/agent-onboarding/SKILL.md[ 03 / 04 ]
·
Pricing
Loading pricing...
[ 04 / 04 ]
·
FAQ
//
FAQ
//
Frequently asked questions
Everything you need to know about Firecrawl Scrape.
General
How It Works
Pricing