Linkup / deep web research report (async)
Linkup tool linkup-research-post on looot: input fields, $1.5 per call, output shape, and code to run it with curl, JavaScript or Python.
Start an asynchronous deep research task on a question: Linkup searches the web and writes a sourced report. reasoningDepth S, M, L or XL sets depth and price. Read the result with linkup-research.
- Tool id:
linkup-research-post - Provider: Linkup
- Job: Research web (
web.research) - Price: $1.5 per call. A call that fails at the provider costs $0.
Inputs
| Name | Type | Required | Description |
|---|---|---|---|
excludeDomains |
array | no | The domains you want to exclude of the search. By default, don’t restrict the search. |
fromDate |
string | no | The date from which the search results should be considered, in ISO 8601 format (YYYY-MM-DD). It must be before toDate, if provided, and later than 1970-01-01. Example: “2025-01-01” |
includeDomains |
array | no | The domains you want to search on. By default, don’t restrict the search. You can provide up to 100 domains. |
mode |
string | no | answer, auto (default), investigate or research. |
outputType |
string | yes | Output type: sourcedAnswer or structured. structured also needs structuredOutputSchema. Example: “sourcedAnswer” |
q |
string | yes | The natural language question for which you want to retrieve context. Example: “What is Microsoft’s 2024 revenue?” |
reasoningDepth |
string | no | S, M, L or XL. Price: S $0.25, M $0.50, L $1.50 (default), XL $2.50. Example: “S” |
structuredOutputSchema |
string | no | Required only when outputType is structured. Provide a JSON schema (as a string) representing the desired response format. The root must be of type object. |
toDate |
string | no | The date until which the search results should be considered, in ISO 8601 format (YYYY-MM-DD). It must be later than fromDate, if provided, or than 1970-01-01. Example: “2025-06-30” |
Output
The run’s result holds the provider’s answer. Signed in, looot inspect linkup-research-post prints its fields.
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":"linkup-research-post","input":{"q":"What is Microsoft'\''s 2024 revenue?","outputType":"sourcedAnswer","toDate":"2025-06-30","fromDate":"2025-01-01","excludeDomains":["wikipedia.org"],"includeDomains":["microsoft.com","agolution.com"],"reasoningDepth":"S"},"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: "linkup-research-post",
input: {
q: "What is Microsoft's 2024 revenue?",
outputType: "sourcedAnswer",
toDate: "2025-06-30",
fromDate: "2025-01-01",
excludeDomains: ["wikipedia.org"],
includeDomains: ["microsoft.com", "agolution.com"],
reasoningDepth: "S",
},
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": "linkup-research-post",
"input": {
"q": "What is Microsoft's 2024 revenue?",
"outputType": "sourcedAnswer",
"toDate": "2025-06-30",
"fromDate": "2025-01-01",
"excludeDomains": ["wikipedia.org"],
"includeDomains": ["microsoft.com", "agolution.com"],
"reasoningDepth": "S",
},
"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.research as endpointId; see the job page.