Skip to content
looot docs
Esc
↑↓navigate↵open⌘Jpreview
On this page

Hyperbrowser

Hyperbrowser on looot as of 2026-09-28: 16 jobs through 16 endpoints, how you reach it, what it costs, and how to run it.

Hyperbrowser

Web dataSEO/AEO16 jobs, 16 endpoints

What it’s good for

Hyperbrowser is in Web data, SEO/AEO. Reach for it to search the web and get ranked results; scrape a web page into markdown; crawl api.

As of 2026-09-28 (catalog revision 85280) it serves 16 jobs through 16 endpoints.

Jobs

Job id What it does Endpoints
api.crawl Crawl api 1
api.extract Extract api 1
api.scrape Scrape api 1
api.scrape.batch Batch api scrape 1
api.task.browser-use Browser use api task 1
api.task.claude-computer-use Claude computer use api task 1
api.task.cua Cua api task 1
api.task.gemini-computer-use Gemini computer use api task 1
api.task.grok-computer-use Grok computer use api task 1
api.task.hyper-agent Hyper agent api task 1
api.task.meta-computer-use Meta computer use api task 1
api.web.crawl Crawl api web 1
web.scrape.markdown Scrape a web page into markdown 1
web.search Search the web and get ranked results 1
x402.web.fetch Fetch x402 web 1
x402.web.search Search x402 web 1

Access

  • Runs on looot’s key for 16 endpoints: nothing to set up, the run spends your looot balance. You can connect your own key instead; see Bring your own key.

Price basis

11 per call (from $0.001), 5 per result (from $0.001). A call that fails at the provider costs $0; see What’s free.

Free first in fallback

Partly. 5 endpoints bill per result, so a miss costs nothing and fallback can move them ahead of flat-priced rows. See Free first.

Run it

A job run takes shared input names, not Hyperbrowser’s own field names; looot maps them for each provider. For job:web.scrape.markdown, url is taken by 4 of its 4 providers. See Job inputs.

Example input for looot run or the MCP run tool, with placeholder values:

looot run job:web.scrape.markdown --input '{"url":"https://example.com"}'
{
  "endpointId": "job:web.scrape.markdown",
  "input": {
    "url": "https://example.com"
  },
  "idempotencyKey": "<new unique key>"
}

A job run picks among all the job’s providers. To run Hyperbrowser itself, name one of its endpoints (MCP search with {"filters": {"provider": "hyperbrowser"}} lists them), for example hyperbrowser-api-web-fetch: looot inspect hyperbrowser-api-web-fetch prints its exact input fields and price.

In the live catalog

Hyperbrowser’s name and logo are trademarks of their owner, shown to identify the provider.

Was this page helpful?