Run a web research task

Run job:research.task.run through the looot API: 1 provider, from $0.01 per call. Inputs, prices, output shape and code for curl, JavaScript and Python.

Run a web research task.

Job id research.task.run, in Web search & research (Research agents). As of 2026-10-01, 1 provider serve it through 1 tool. Run job:research.task.run and looot picks one of them; with fallback on, a miss moves on to the next. See Jobs.

Inputs

This job has one tool, so it takes that tool’s fields. Any key you send passes through unchanged.

Name	Type	Required	Description
`advanced_settings`	string	no	Advanced search configuration for the task run.
`enable_events`	string	no	Controls tracking of task run execution progress. When set to true, progress events are recorded and can be accessed via the Task Run events endpoint. When false, no progress events are tracked. Note that progress tracking cannot be enabled after a run has been created. The flag is set to true by default for premium processors (pro and above).
`input`	string	yes	Input to the task, either text or a JSON object. Example: “What was the GDP of France in 2023?”
`mcp_servers`	string	no	Optional list of MCP servers to use for the run.
`memory_scope_key`	string	no	User-provided key identifying the memory scope to use. Omit to use personal memory, if available.
`metadata`	string	no	User-provided metadata stored with the run. Keys and values must be strings with a maximum length of 16 and 512 characters respectively.
`previous_interaction_id`	string	no	Interaction ID to use as context for this request.
`processor`	string	yes	Processor to use for the task. Example: “base”
`source_policy`	string	no	Optional source policy governing included and excluded domains and domain/path prefixes in web search results.
`task_spec`	string	no	Task specification. If unspecified, defaults to auto output schema.
`webhook`	string	no	Callback URL (webhook endpoint) that will receive an HTTP POST when the run completes. This feature is not available via the Python SDK.

Providers and prices

Provider	Tool	Price
Parallel	`parallel-tasks-runs`	$0.01 per call

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

Output

The run’s result holds the provider’s answer. Signed in, looot inspect parallel-tasks-runs 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":"job:research.task.run","input":{"processor":"base","input":"What was the GDP of France in 2023?"},"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:research.task.run",
    input: {
      processor: "base",
      input: "What was the GDP of France in 2023?",
    },
    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:research.task.run",
        "input": {
            "processor": "base",
            "input": "What was the GDP of France in 2023?",
        },
        "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:research.task.run.