Firecrawl API · Web Data
Search the web and scrape results with the Firecrawl API
Searches the web and can scrape each result. You call it with one looot token, no Firecrawl account needed. It takes query as required input. Each call costs $0.001 per result. Over the last 30 days looot ran it 65 times: 100% finished without an error, median answer 1.4 s. Answers follow a stored output format checked on real answers.
- Price
- $0.001 per result
- Success rate, 30 days
- 100%
- Runs, 30 days
- 65
- Access
- looot token only
Search the web and scrape results: call it from code
One POST to /v1/runs with your looot token, the endpoint id firecrawl-search and an input. Values come from the stored input schema; a value in <angle brackets> is a placeholder the schema gives no example for.
| Input | Type | Value shown |
|---|---|---|
| query | string | placeholder |
POST /v1/runs
curl -X POST 'https://api.looot.ai/v1/runs?wait=true' \
-H 'Authorization: Bearer YOUR_LOOOT_TOKEN' \
-H 'Content-Type: application/json' \
-d '{"endpointId":"firecrawl-search","input":{"query":"<string>"},"idempotencyKey":"<unique-idempotency-key>"}'import uuid
import requests
response = requests.post(
"https://api.looot.ai/v1/runs?wait=true",
headers={"Authorization": "Bearer YOUR_LOOOT_TOKEN"},
json={
"endpointId": "firecrawl-search",
"input": {
"query": "<string>",
},
"idempotencyKey": str(uuid.uuid4()),
},
)
print(response.json())const response = await fetch("https://api.looot.ai/v1/runs?wait=true", {
method: "POST",
headers: {
Authorization: "Bearer YOUR_LOOOT_TOKEN",
"Content-Type": "application/json",
},
body: JSON.stringify({
endpointId: "firecrawl-search",
input: {
"query": "<string>"
},
idempotencyKey: crypto.randomUUID(),
}),
});
console.log(await response.json());Response: verified on real answers
{ id, data: { web: { url, title, position, description }[] }, success, creditsUsed }validated on 3 real answers.
Price and reliability
- Price formula
- $0.0010 per result
- Most one run can cost
- $0.001
- Success rate, 30 days
- 100%
- Runs, 30 days
- 65
- Median answer time
- 1.4 s
- Last success
- Nov 13, 2026
Run numbers are looot's own runs of each endpoint over the last 30 days: the share that completed without an error, and the median time to answer. An endpoint with fewer than 10 runs in that window shows "not enough runs to rank" and is never ranked. Prices are what looot charges per call or per result, fee included, read from the live catalog; you prepay credit and each call is charged when it runs.
Other providers for this job
| Endpoint | Price | Success rate, 30 days |
|---|---|---|
| Search the webTinyFish Search API | free | 83.3% of 21,959 runs |
| Search the web (Google)Limadata | $0.002 per call | 99.5% of 3,713 runs |
| Search the web and read the resultsContext.dev | $0.00025 per result | 99.8% of 1,306 runs |
| Neural web searchExa | $0.007 per call | 99.8% of 1,077 runs |
| Search the webBrave Search | $0.005 per call | 100% of 48 runs |
| Search the webLinkup | $0.005 per call | 100% of 18 runs |
More Firecrawl endpoints
- Scrape a web page
$0.005 per call
94.1% of 2,805 runs
- Map multiple URLs based on options
$0.005 per call
100% of 48 runs
- Crawl multiple URLs based on options
$0.005 per result
not enough runs to rank
- Extract structured data from pages using LLMs
$0.000333 per result
not enough runs to rank
- Get an extract job's status
$0.000333 per result
not enough runs to rank
Questions about the Firecrawl API on looot
Give your agent every data provider, one key.
Everyone gets $2 in free credits once after sign-in and workspace selection. Then pay only for what you use.