From Web Pages to Usable Data
Get the content your application needs without managing fetchers, browsers, parsing, or background jobs.
Web infrastructure for AI.
Scrape clean content. Extract structured data. Crawl websites. Monitor changes. Give your AI agents and applications access to the web through one API.
One API. Four Core Operations.
Go from a single page to a website or a recurring check, with the same API key and workflow.
Credit-Based Pricing That Stays Simple
Start with 100 free credits.
Buy more when you need them. No subscription required.
One API for the live web
Build AI agents, research tools, and data pipelines with content you can use and changes you can track.
Start with a URL. Choose the content you need. Use the result in your next step.
- Scrape articles and documentation into clean Markdown
- Extract product details or pricing into validated JSON
- Crawl a website with page limits and URL filters
- Watch prices, job listings, or selected fields for changes
Scrape
A page, ready to use.
Turn a URL into clean content for your app, knowledge base or AI agent.
/scrape# Getting startedFrom the web to your workflow.Clean content. Ready for your next step.[Read the guide](/docs)
Extract
Only the fields you need.
Go from a page to structured JSON. Describe your data or bring your own schema.
/extract{ "name": "Pro", "price": 29, "billing": "monthly"}
Crawl
One URL. The whole picture.
Follow links across a site and collect its content, with boundaries you control.
/crawlexample.comStart URL
├/docs/getting-started✓
├/docs/api-reference✓
└/pricing✓
Watch
Know when the web changes.
Check pages on a schedule. Track content or specific fields and get the diff.
/watchpricing.monthlyChanged
−"price": 19Before
+"price": 29After
One API key. Fits your stack.
Simple credit-based pricing
One credit balance for Scrape, Extract, Crawl and Watch.
Buy credits once
1 credit per successful page or Watch check, plus 3 when AI is used. Screenshots included.
- Pay for successful pages and Watch checks
- Credits never expire
- Lower effective rates on larger credit packs
Total price
Free Frequently asked questions
What to know before connecting your application to the web.
CrawlKit turns web pages into usable data for AI agents and applications. Scrape a page, extract structured JSON, crawl a website, or watch content for changes through one API.
Create an account for 100 free credits, open the dashboard Playground, and choose Scrape. Enter a URL to inspect a real response, then create an API key for your application. No credit card is needed to start.
Scrape returns page content as Markdown, HTML, text, metadata, links or a screenshot. Extract returns structured JSON from a schema or instruction. Schema-based output is validated before a request succeeds.
Use Crawl to discover and fetch multiple pages from a website. Set page and depth limits, include or exclude paths, and retrieve the results as the job progresses. The default is 100 pages at depth 2, with a maximum of 1,000 pages.
Watch checks a URL on a schedule and compares normalized content or extracted fields. The first successful check creates a baseline. Later changes produce before/after data and a diff, with optional signed webhooks. Checks default to hourly; the minimum interval is 15 minutes. Change history is kept for 30 days.
Each successful page costs 1 credit, plus 3 if AI is used. Crawl is charged per successful page. Each successful Watch check uses the same rate, even when nothing changes. Screenshots are included. Unused reservations are refunded.
Credits never expire. Start with 100 free credits and buy more when you need them. There is no monthly subscription requirement, and larger credit packs reduce the price per credit.
No. Standard scraping does not require an LLM. Extraction can read suitable embedded data directly; an LLM can handle instruction-based or other schema requests when configured. You can test your target page in the Playground.
Yes. The MCP server exposes Scrape, Extract, Crawl and Watch tools to compatible clients. You can also call the HTTP API directly with your API key in the Authorization header.
HTML pages, JavaScript rendering and bounded PDF parsing are supported. Scanned PDFs can use optional English or Turkish OCR. Some protected sites may still reject requests, and scrolling remains bounded by configured steps and time. Test the pages you need before building a workflow around them.
Crawl returns a job ID. Scrape and Extract can also return HTTP 202 while work continues. Poll the job endpoint until it completes or fails.
Give your next workflow access to the web.
Start with 100 free credits. Try a real URL in the Playground, inspect the output, and connect your API key.
