Octen / Broad search across sub-queries

Octen tool octen-search on looot: input fields, $0.03 per call, output shape, and code to run it with curl, JavaScript or Python.

Splits one query into several sub-queries from different angles, searches them at once and returns results grouped by sub-query. Send query; max_queries caps the sub-queries.

Tool id: octen-search
Provider: Octen
Job: Search the web and get ranked results (web.search)
Price: $0.03 per call. A call that fails at the provider costs $0.

Inputs

Name	Type	Required	Description
`max_queries`	integer	no	Upper bound on generated sub-queries. Octen allows up to 30; bounded here to 5.
`query`	string	yes	The original search query; Octen expands it into sub-queries. Example: “open source vector databases”
`search_options`	object	no

Output

Shape of the run’s result, checked against 1 real answer:

{ code, data: { query, queries: string[], search_results: { query, latency, results: { ... }[] }[] }, meta: { usage: { num_search_queries, full_content_tokens, full_content_extra_count }, latency }, request_id }

Every call needs your API token in LOOOT_TOKEN; Sign in shows how to get one. Each run also needs a new idempotency key, so a retry never pays twice. With wait: 30 the answer comes back inline when the run ends within 30 seconds. Otherwise you get the running run back: poll GET /v1/runs/<runId>.

Example input with placeholder values:

curl -X POST "https://api.looot.ai/v1/runs" \
  -H "Authorization: Bearer $LOOOT_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"endpointId":"octen-search","input":{"query":"open source vector databases"},"wait":30}'

const response = await fetch("https://api.looot.ai/v1/runs", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.LOOOT_TOKEN}`,
    "Content-Type": "application/json",
    "Idempotency-Key": crypto.randomUUID(),
  },
  body: JSON.stringify({
    endpointId: "octen-search",
    input: {
      query: "open source vector databases",
    },
    wait: 30,
  }),
});
const run = await response.json();
console.log(run.status, run.result);

import os
import uuid

import requests

response = requests.post(
    "https://api.looot.ai/v1/runs",
    headers={
        "Authorization": f"Bearer {os.environ['LOOOT_TOKEN']}",
        "Idempotency-Key": str(uuid.uuid4()),
    },
    json={
        "endpointId": "octen-search",
        "input": {
            "query": "open source vector databases",
        },
        "wait": 30,
    },
    timeout=90,
)
run = response.json()
print(run["status"], run.get("result"))

To let looot pick among every provider of this job instead, send job:web.search as endpointId; see the job page.

Octen / Broad search across sub-queries

Inputs

Output

Run it