ScrapeGraphAI
ScrapeGraphAI on looot as of 2026-10-07: 9 jobs through 11 endpoints, how you reach it, what it costs, and how to run it.
ScrapeGraphAI
What it’s good for
ScrapeGraphAI is in Enrichment, Scrapers, Web search & research. Reach for it to search the web and get ranked results; scrape a web page into markdown; scrape a URL into structured JSON.
As of 2026-10-07 (catalog revision 101776) it serves 9 jobs through 11 endpoints.
Jobs
| Job id | What it does | Endpoints |
|---|---|---|
web.scrape.markdown |
Scrape a web page into markdown | 2 |
web.scrape.structured |
Scrape a URL into structured JSON | 2 |
company.branding |
Branding company | 1 |
web.crawl |
Crawl web | 1 |
web.crawl.results |
Results web crawl | 1 |
web.crawl.status |
Status web crawl | 1 |
web.screenshot |
Take a screenshot of a web page | 1 |
web.search |
Search the web and get ranked results | 1 |
web.search.answer |
Answer web search | 1 |
Access
- Access is shown per endpoint in search results; see Access.
Price basis
6 per call (from $0.002), 3 per result (from $0.0024), 2 free. A call that fails at the provider costs $0; see What’s free.
Free first in fallback
Yes. 2 endpoints cost $0, and a $0 row is tried ahead of the paid rows in its bucket. See Free first.
Run it
Name one of its endpoints, for example scrapegraphai-scrape. looot inspect scrapegraphai-scrape (MCP inspect) prints its exact input fields and price, then looot run scrapegraphai-scrape --input '<JSON>' (MCP run) with those fields.
In the live catalog
- Browse: looot.ai/public-catalog/scrapegraphai-scrape, or search looot.ai/public-catalog for ScrapeGraphAI.
- Every endpoint, no account needed:
curl "https://api.looot.ai/v1/public-catalog?provider=scrapegraphai"