# ScrapeGraphAI on looot

ScrapeGraphAI gives your agent 9 jobs through looot: scrape a URL into structured JSON, scrape a web page into markdown, results web crawl and 6 more jobs. 11 endpoints run today, some of them free.

## At a glance

- Category: Enrichment
- Access: Runs on looot's platform key: you do not need your own ScrapeGraphAI account
- Price: some free

## Choose it when

- You want the lowest price to results web crawl: free, the cheapest of 2 providers on looot.
- You want the lowest price to status web crawl: free, the cheapest of 2 providers on looot.
- You want the lowest price to answer web search: $0.01 per result, the cheapest of 2 providers on looot.
- You need to branding company: ScrapeGraphAI is the only provider on looot that runs this job today.

## Endpoints and jobs

| Endpoint | Job | Price | Runs (30 days) | Benchmark |
|---|---|---|---|---|
| [AI extract](/public-catalog/scrapegraphai-extract) | `web.scrape.structured` | $0.01 per call | 98.6% of 844 runs without an error, median 4.1 s | [Scrape a URL into structured JSON](/benchmarks/web-scrape-structured) |
| [Scrape page (stealth)](/public-catalog/scrapegraphai-scrape-stealth) | `web.scrape.markdown` | $0.012 per call | 4.5% of 22 runs without an error, median 1.0 s | [Scrape a web page into markdown](/benchmarks/web-scrape-markdown) |
| [Scrape page](/public-catalog/scrapegraphai-scrape) | `web.scrape.markdown` | $0.002 per call | 78.6% of 14 runs without an error, median 1.1 s | [Scrape a web page into markdown](/benchmarks/web-scrape-markdown) |
| [Crawl pages](/public-catalog/scrapegraphai-crawl-pages) | `web.crawl.results` | free | not enough runs to rank | no benchmark yet |
| [Crawl status](/public-catalog/scrapegraphai-crawl-status) | `web.crawl.status` | free | not enough runs to rank | no benchmark yet |
| [Crawl website (start)](/public-catalog/scrapegraphai-crawl-start) | `web.crawl` | $0.0024 per result | not enough runs to rank | no benchmark yet |
| [Screenshot](/public-catalog/scrapegraphai-screenshot) | `web.screenshot` | $0.004 per call | not enough runs to rank | no benchmark yet |
| [Search and read pages](/public-catalog/scrapegraphai-search) | `web.search` | $0.004 per result | not enough runs to rank | [Search the web and get ranked results](/benchmarks/web-search) |
| [Scrape to JSON](/public-catalog/scrapegraphai-scrape-json) | `web.scrape.structured` | $0.01 per call | not enough runs to rank | [Scrape a URL into structured JSON](/benchmarks/web-scrape-structured) |
| [Search and extract](/public-catalog/scrapegraphai-search-extract) | `web.search.answer` | $0.01 per result | not enough runs to rank | no benchmark yet |
| [Brand kit from website](/public-catalog/scrapegraphai-branding) | `company.branding` | $0.05 per call | not enough runs to rank | no benchmark yet |

## How the numbers are measured

Run numbers are looot's own runs of each endpoint over the last 30 days: the share that completed without an error, and the median time to answer. An endpoint with fewer than 10 runs in that window shows "not enough runs to rank" and is never ranked. Prices are what looot charges per call or per result, fee included, read from the live catalog; you prepay credit and each call is charged when it runs.

Read 2026-11-10 23:22 UTC.

## For agents

The minimal request for AI extract (`scrapegraphai-extract`). Replace each <placeholder> with your value and send a new idempotency key per run.

### MCP

```json
{
  "endpointId": "scrapegraphai-extract",
  "input": {},
  "idempotencyKey": "<a new id per run>"
}
```

### REST

```bash
curl -X POST https://api.looot.ai/v1/runs \
  -H "Authorization: Bearer $LOOOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"endpointId":"scrapegraphai-extract","input":{},"idempotencyKey":"<a new id per run>"}'
```

### CLI

```bash
looot run scrapegraphai-extract --input '{}'
```