Parallel
Parallel on looot as of 2026-09-28: 4 jobs through 4 endpoints, how you reach it, what it costs, and how to run it.
Parallel
What it’s good for
Parallel is in SEO/AEO, Web data. Reach for it to search the web and get ranked results; get extract; runs tasks.
As of 2026-09-28 (catalog revision 85280) it serves 4 jobs through 4 endpoints.
Jobs
| Job id | What it does | Endpoints |
|---|---|---|
extract.get |
Get extract | 1 |
tasks.runs |
Runs tasks | 1 |
v1beta.findall.runs |
Runs v1beta findall | 1 |
web.search |
Search the web and get ranked results | 1 |
Access
- Runs on looot’s key for 4 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
3 per call (from $0.005), 1 per result (from $0.001). A call that fails at the provider costs $0; see What’s free.
Free first in fallback
Partly. 1 endpoint 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 Parallel’s own field names; looot maps them for each provider. For job:extract.get, url is taken by 1 of its 3 providers. See Job inputs.
Example input for looot run or the MCP run tool, with placeholder values:
looot run job:extract.get --input '{"url":"https://example.com"}'{
"endpointId": "job:extract.get",
"input": {
"url": "https://example.com"
},
"idempotencyKey": "<new unique key>"
}A job run picks among all the job’s providers. To run Parallel itself, name one of its endpoints (MCP search with {"filters": {"provider": "parallel"}} lists them), for example parallel-extract: looot inspect parallel-extract prints its exact input fields and price.
In the live catalog
- Browse: looot.ai/public-catalog/parallel-extract, or search looot.ai/public-catalog for Parallel.
- Every endpoint, no account needed:
curl "https://api.looot.ai/v1/public-catalog?provider=parallel"
Parallel’s name and logo are trademarks of their owner, shown to identify the provider.