Parallel API API · Web Data
Search with the Parallel API API
Searches the web. You call it with one looot token, no Parallel API account needed. It takes search_queries as required input. Each call costs $0.005 per call. It has fewer than 10 looot runs in the last 30 days, so no success rate is shown yet. Answers follow a stored output format checked on real answers.
- Price
- $0.005 per call
- Success rate, 30 days
- not enough runs yet
- Runs, 30 days
- under 10
- Access
- looot token only
Search: call it from code
One POST to /v1/runs with your looot token, the endpoint id parallel-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 |
|---|---|---|
| search_queries | array of 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":"parallel-search","input":{"search_queries":["<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": "parallel-search",
"input": {
"search_queries": [
"<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: "parallel-search",
input: {
"search_queries": [
"<string>"
]
},
idempotencyKey: crypto.randomUUID(),
}),
});
console.log(await response.json());Response: verified on real answers
{ usage: { name, count }[], results: { url, title, excerpts: string[], publish_date }[], metadata, warnings, search_id, session_id }validated on 2 real answers.
Price and reliability
- Price formula
- $0.0010 to $0.0050 per call by `mode` (fast $0.0010, basic $0.0050, turbo $0.0010, advanced $0.0050)
- Most one run can cost
- $0.005
- Success rate, 30 days
- not enough runs yet
- Runs, 30 days
- not enough runs yet
- Median answer time
- not enough runs yet
- Last success
- not recorded
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 web and scrape resultsFirecrawl | $0.001 per result | 100% of 65 runs |
| Search the webBrave Search | $0.005 per call | 100% of 48 runs |
More Parallel API endpoints
- Extract
$0.001 per result
85.7% of 14 runs
- Create FindAll Run
$0.25 per call
not enough runs to rank
- Create Task Run
$0.01 per call
not enough runs to rank
Questions about the Parallel API 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.