Brave / Search the web

Brave Search tool brave-search-res-web-search on looot: input fields, $0.005 per call, output shape, and code to run it with curl, JavaScript or Python.

Returns web results from Brave’s independent index, with optional news, videos, FAQ, discussions and infobox blocks. Send q; country, search_lang, freshness, count and result_filter refine it. Charged per request.

Tool id: brave-search-res-web-search
Provider: Brave Search
Job: Search the web and get ranked results (web.search)
Price: $0.005 per call. A call that fails at the provider costs $0.

Inputs

Name	Type	Required	Description
`count`	integer	no	Number of results (web up to 20).
`country`	string	no	Two-letter country code, e.g. US, FR.
`freshness`	string	no	pd (day), pw (week), pm (month), py (year) or YYYY-MM-DDtoYYYY-MM-DD.
`offset`	integer	no	Page offset (0-9).
`q`	string	yes	Search query (max 400 characters, 50 words).
`result_filter`	string	no	Comma list of result types: web, news, videos, faq, discussions, infobox, locations, summarizer.
`safesearch`	string	no	off, moderate or strict.
`search_lang`	string	no	Language of results, e.g. en, fr.
`summary`	boolean	no	true to get a summarizer key for /res/v1/summarizer/search (Pro plans).

Output

Shape of the run’s result, checked against 20 real answers:

{ faq: { type, results: { url, title, answer, meta_url: { ... }, question }[] }, web: { type, results: { qa: { ... }, age, faq: { ... }, url, type, title, video: { ... }, article: { ... }, cluster: { ... }[], is_live, profile: { ... }, subtype, language, location: { ... }, meta_url: { ... }, page_age, software: { ... }, thumbnail: { ... }, description, cluster_type, deep_results: { ... }, organization: { ... }, creative_work: { ... }, extra_snippets: string[], is_source_both, family_friendly, is_source_local }[], family_friendly }, type, mixed: { top: unknown[], main: { all, type, index }[], s... ...

The shape is cut here. Signed in, looot inspect brave-search-res-web-search prints all of it.

Run it

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":"brave-search-res-web-search","input":{"q":"<q>"},"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: "brave-search-res-web-search",
    input: {
      q: "<q>",
    },
    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": "brave-search-res-web-search",
        "input": {
            "q": "<q>",
        },
        "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.