WEB DATA FOR AI
BUILT FOR THE AI ERA
Turn any webpage into clean, structured data with one API call.
Get an API key in a few clicks.
Convert any webpage to clean, well-formatted Markdown. Documentation, content migration, or preparing context for LLMs.
curl -X POST \
https://v2-api.scrapegraphai.com/api/scrape \
-H "Content-Type: application/json" \
-H "SGAI-APIKEY: $SGAI_API_KEY" \
-d '{
"url": "https://docs.example.com/getting-started",
"formats": [
{
"type": "markdown"
}
]
}'{
"markdown": "# Getting started\n\nA clean, structured page...",
"status": "success"
}// WHY SCRAPEGRAPHAI
Convert any webpage to clean, well-formatted Markdown. Documentation, content migration, or preparing context for LLMs.
curl -X POST \
https://v2-api.scrapegraphai.com/api/scrape \
-H "Content-Type: application/json" \
-H "SGAI-APIKEY: $SGAI_API_KEY" \
-d '{
"url": "https://docs.example.com/getting-started",
"formats": [
{
"type": "markdown"
}
]
}'{
"markdown": "# Getting started\n\nA clean, structured page...",
"status": "success"
}Extract structured data from any webpage using natural language prompts. Define a schema and get back clean JSON — product details, contact info, or any content.
curl -X POST \
https://v2-api.scrapegraphai.com/api/extract \
-H "Content-Type: application/json" \
-H "SGAI-APIKEY: $SGAI_API_KEY" \
-d '{
"url": "https://news.ycombinator.com",
"prompt": "Extract the top 3 stories with title, points, and author"
}'{
"stories": [
{
"title": "The scraper for the AI Era",
"points": 248,
"author": "scrapegraph"
}
]
}Search the web and extract structured data from results in one call. Market research, competitor analysis, and trend tracking.
curl -X POST \
https://v2-api.scrapegraphai.com/api/search \
-H "Content-Type: application/json" \
-H "SGAI-APIKEY: $SGAI_API_KEY" \
-d '{
"query": "sustainable packaging trends 2026",
"numResults": 3,
"prompt": "Extract top trends with market size",
"locationGeoCode": "us"
}'{
"results": [
{
"trend": "Reusable packaging",
"market_size": "$42B"
}
]
}Crawl all the pages on a website and get structured data for each link. Site-wide extraction, content audits, and data pipelines.
curl -X POST \
https://v2-api.scrapegraphai.com/api/crawl \
-H "Content-Type: application/json" \
-H "SGAI-APIKEY: $SGAI_API_KEY" \
-d '{
"url": "https://docs.example.com"
}'{
"pages": 128,
"processed": 128,
"status": "success"
}Watch webpages for changes and get notified via webhook. Price tracking, content updates, and competitor intelligence.
curl -X POST \
https://v2-api.scrapegraphai.com/api/monitor \
-H "Content-Type: application/json" \
-H "SGAI-APIKEY: $SGAI_API_KEY" \
-d '{
"url": "https://example-shop.com/product",
"interval": "0 */6 * * *",
"webhookUrl": "https://your-app.com/webhook",
"formats": [
{
"type": "markdown"
}
]
}'{
"monitor_id": "mon_01J...",
"interval": "0 */6 * * *",
"status": "active"
}// BUILT FOR EVERY WORKFLOW
Track competitor prices on Amazon, eBay, and other e-commerce sites. Get alerts when prices drop or inventory changes.
Read more
Extract LinkedIn profiles, Twitter accounts, and contact information at scale without getting blocked.
Read more
Aggregate reviews, ratings, and sentiment from multiple sites. Build comprehensive competitor analysis.
Read more
Monitor property listings on Zillow, Redfin, and local sites. Track price changes and new listings.
Read more
Connect AI assistants directly to the web via Model Context Protocol. Enable Claude, Cursor, and other AI tools to scrape data in real-time.
Read more
Provide agents with extremely fast web access. Perfect for RAG pipelines, autonomous research, and real-time data enrichment.
Read moreDon't see your use case? Our AI adapts to any website structure.
// AI ASSISTANT INTEGRATION
// CONNECT WITH YOUR STACK
// CHOOSE THE PLAN THAT FITS YOUR NEEDS
For individuals
billed monthly
For growing businesses
billed monthly
For data-driven teams
billed monthly
For large organizations
custom billing
Contact salesAll requests are SOC 2 Type II compliant.
// ONE-TIME CREDIT TOP-UPS
Credit packs never expire and stack on top of your monthly subscription.
1,000 credits · $5.00 per 1k credits
10,000 credits · $4.00 per 1k credits
50,000 credits · $3.00 per 1k credits
// HOW CREDITS WORK
| Endpoint | Base cost | Formula |
|---|---|---|
| ScrapeConvert any URL to clean markdown, HTML, screenshots, or branding analysis | 1 (markdown) 2 (screenshot) 25 (branding) | format base + stealth modifier |
| ExtractExtract structured data from any webpage using natural language prompts | 5 | 5 + stealth modifier |
| SearchSearch the web and extract data from results in one call | 2/result (no prompt) 5/result (with prompt) | (base + stealth modifier) × results |
| CrawlCrawl entire websites and extract data from every page | 2 startup + per-page scrape cost | 2 + (format base + stealth modifier) × pages |
| MonitorWatch webpages for changes and get notified via webhook | +5 on change detected | format base + stealth modifier + change bonus |
| PDF processingFinal billing uses actual processed pages; maxPages caps the PDF reservation | 1 credit/page 25-page default cap | 1 × processed pages |
// EXTRA FEATURES
| Fetch setting | Credit modifier |
|---|---|
| Render mode: auto / fast / jsChanges the fetch strategy. Render mode does not change the credit cost. | +0 |
| Stealth toggleAdds anti-bot bypass on top of the selected render mode. | +5 |
// ESTIMATE YOUR COSTS
URL to markdown, HTML, screenshot
Auto mode uses the cheapest approach first.
// HOW WE COMPARE
| Feature | ScrapeGraphAI | Scrapy | BeautifulSoup | Selenium |
|---|---|---|---|---|
| AI-Powered Extraction | ||||
| Zero Maintenance | ||||
| Automatic Proxy Management | ||||
| JavaScript Rendering | ||||
| Auto-Adapts to Changes | ||||
| Built-in Rate Limiting | ||||
| Cloud-Ready API | ||||
| AI-Agent Ready | ||||
| Enterprise Support |
// LATEST FROM THE BLOG
ScrapeGraphAI V2 brings scrape, extract, search, crawl, monitor, events, and history into one cleaner API for production web data workflows.
Francesco Zuppichini · Apr 24, 2026READ MORE →Install just-scrape and run AI-powered scraping, extraction, search, and crawling from your terminal.
Marco Vinciguerra · May 30, 2026READ MORE →[ 03 ] · TUTORIALSConnect Claude, Cursor, and any MCP client to live web data with the hosted endpoint or a local install.
Marco Vinciguerra · Jun 26, 2026READ MORE →// FAQ
ScrapeGraphAI is an AI-powered web scraping API that lets you extract structured data from any website using natural language prompts. No complex selectors, no brittle scripts. Just describe what you want and get clean JSON back.
You send a URL and a natural language prompt describing the data you need. Our AI models read and understand the page content, then extract exactly the fields you asked for, returned as structured JSON. It handles dynamic content, SPAs, and messy HTML automatically.
No. ScrapeGraphAI uses large language models to understand page content semantically. You describe what you want in plain English. No selectors, no regex, no DOM traversal. The AI figures out where the data lives.
All responses come back as structured JSON matching your prompt. You can also provide a JSON schema to enforce exact output shapes, perfect for feeding data directly into your pipeline or database.
There is no free subscription tier on this site. Paid plans start at $20 per month with 10,000 credits, and one-time credit packs are available for extra usage.
Yes. ScrapeGraphAI handles JavaScript-heavy pages, single-page applications, and dynamically loaded content out of the box. No need to manage headless browsers yourself.
Most requests complete in 2-10 seconds depending on page complexity and the amount of data extracted. Frequently requested URLs are cached, so repeat calls come back almost instantly.
Yes. We provide an official MCP (Model Context Protocol) server so AI agents like Claude, Cursor, and Windsurf can use ScrapeGraphAI as a tool directly. Install it with one command and your agent gets web scraping superpowers.
READY TO START
