README.md

★ Check OSS self-host version

NEW Finally, your favorite open-source crawler is now a hosted API.Your open-source crawler, now hosted.

Crawl4AI now available on Cloud

Turn any URL into clean Markdown, typed JSON, or search results. Fast, affordable, and efficient - no infra, no signup.

★ stars71,073 downloads1.9M / mo python3.10 | 3.11 | 3.12 | 3.13 licenseApache-2.0 chatDiscord

POST api.crawl4ai.com/scrape

$ crawl scrape ✎

--instruction

▸ deep ground the answer in the top results

Live · play limits✓ 200 OK

# Type a URL above and hit Run - real output renders here

## What you get #

/scrape URL → clean Markdown, boilerplate stripped, ready for a prompt.
/extract URL + a plain-English ask → typed JSON records. No selectors.
/search query → ranked results as JSON - add rich=1 for follow-ups, related & more.
/answer a question → a direct answer with its sources. Experimental.
at scale queues, jobs, retries, and solid proxies - handled for you.

## Use it in Claude Code, Cursor & agents - paste one line #

Same key everywhere. Mint one above and it drops into each line below.

Ask your agentone line in its chat: it reads llms.txt and sets itself up

set up crawl4ai - https://crawl4ai.com/llms.txt with key: sk_live_…

Claude Code, Codex, Cursor, Gemini CLI, OpenCode, OpenClaw, or any agent that reads a URL · open llms.txt

MCPyour agent's tools, one line per tool

claude mcp add --transport http crawl4ai https://api.crawl4ai.com/mcp --header "Authorization: Bearer sk_live_…"

HTTPcode or curl, any language: base url + key

export CRAWL4AI_URL=https://api.crawl4ai.com CRAWL4AI_KEY=sk_live_…

curl -s "https://api.crawl4ai.com/search?q=web+scraping" -H "Authorization: Bearer sk_live_…"

## Self-host, or skip the setup #

// run it yourself

Self-host

It's Apache-2.0. pip install crawl4ai, point it at your own boxes and proxies. No gate, no token. It's yours.

★ Clone the repo

// let us run it

Hosted

Or forget the infra. We've operated this crawler at scale for years - proxies, queues, jobs, the hard parts. You keep the key; we keep it fast.

Get a key →

Who runs it better than the people who built it? Self-host for control; host with us to move fast. Same crawler either way.

## Pricing #

Your favourite open-source crawler, now in the cloud. Credits, not seats: you pay very little and get more than anywhere else.

Try it now: 20 free credits, no signup. Verify your email for your free credit.

tier

price

for

Free

Free credit to start · no card

Prototypes and side projects. 2,500 credits a month, 10 a minute. Get a key

Starter

$10 · $25 · $100 credit packs

Pay as you go. 120 a minute, 10 at a time, 50,000 credits a month. Credit never expires.

Builder

Coming soon

A monthly plan with included credits and higher limits: 600 a minute, 20 at a time, 500,000 credits a month. Tell us you want it

Enterprise

Let's talk

Volume, regions, SLA. Contact us

1 credit = $0.001 · page 0.5 · search 1 · from our archive 0.25 · real browser 1 · hard site 2 *

Soft launch

Prices and the free credit can change while we learn; the live table is /v1/prices. What you bought stays yours and never expires.

## Philosophy #

# we don't hide.
every result carries where it came from - the origin travels with the data.
# and the whole "block the bots" arms race? a phase.
let crawlers crawl.