Search the web and get ranked results

Run job:web.search through the looot API: 11 providers, from $0 per call. Inputs, prices, output shape and code for curl, JavaScript and Python.

Search the web and get ranked results.

Job id web.search, in Web search & research (Search engines). As of 2026-10-01, 11 providers serve it through 12 tools. Run job:web.search and looot picks one of them; with fallback on, a miss moves on to the next. See Jobs.

Inputs

A job run takes shared input names; looot maps them to each provider’s own fields. See Job inputs.

Input	Taken by
`query`	12 of 12 providers
`limit`	9 of 12 providers
`country`	6 of 12 providers
`language`	5 of 12 providers
`page`	3 of 12 providers

Any other key you send passes through unchanged. Each tool’s own fields are on its page below.

Providers and prices

Provider	Tool	Price
TinyFish Search API	`tinyfish-search`	$0 per call
Context.dev	`context-dev-web-search`	$0.00025 per result
Firecrawl	`firecrawl-search`	$0.001 per result
Jina Reader API	`jina-search`	$0.0025 per call
Brave Search	`brave-search-res-web-search`	$0.005 per call
Hyperbrowser	`hyperbrowser-api-web-search`	$0.005 per call
Linkup	`linkup-search`	$0.005 per call
Parallel	`parallel-search`	$0.005 per call
Octen	`octen-web-search`	$0.006 per call
Exa	`exa-search`	$0.007 per call
Tavily Search and Extract API	`tavily-search`	$0.008 per call
Octen	`octen-search`	$0.03 per call

A call that fails at the provider costs $0. See What’s free.

Output

Each provider answers in its own shape. Shape of the run’s result from context-dev-web-search, checked against 2 real answers:

{ query, results: { url, title, markdown: { code, markdown }, relevance, description }[], request_id, key_metadata: { credits_consumed, credits_remaining }, cache_metadata: { age_ms, status } }

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":"job:web.search","input":{"query":"web automation tools","page":2,"fetch":"{}","purpose":"Find an open-source library for parsing PDF invoices in Python","language":"en","location":"US","after_date":"2024-01-01","before_date":"2024-12-31","domain_type":"news","pub_year_max":2022,"pub_year_min":2019,"exclude_domains":"pinterest.com,quora.com","include_domains":"github.com,arxiv.org","recency_minutes":60,"include_thumbnail":"true"},"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: "job:web.search",
    input: {
      query: "web automation tools",
      page: 2,
      fetch: "{}",
      purpose: "Find an open-source library for parsing PDF invoices in Python",
      language: "en",
      location: "US",
      after_date: "2024-01-01",
      before_date: "2024-12-31",
      domain_type: "news",
      pub_year_max: 2022,
      pub_year_min: 2019,
      exclude_domains: "pinterest.com,quora.com",
      include_domains: "github.com,arxiv.org",
      recency_minutes: 60,
      include_thumbnail: "true",
    },
    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": "job:web.search",
        "input": {
            "query": "web automation tools",
            "page": 2,
            "fetch": "{}",
            "purpose": "Find an open-source library for parsing PDF invoices in Python",
            "language": "en",
            "location": "US",
            "after_date": "2024-01-01",
            "before_date": "2024-12-31",
            "domain_type": "news",
            "pub_year_max": 2022,
            "pub_year_min": 2019,
            "exclude_domains": "pinterest.com,quora.com",
            "include_domains": "github.com,arxiv.org",
            "recency_minutes": 60,
            "include_thumbnail": "true",
        },
        "wait": 30,
    },
    timeout=90,
)
run = response.json()
print(run["status"], run.get("result"))

To pin one provider, send its tool id as endpointId instead of job:web.search.