Hyperbrowser API / Start an extract job

Hyperbrowser tool hyperbrowser-api-extract on looot: input fields, $0.02 per call, output shape, and code to run it with curl, JavaScript or Python.

Start an extract job Send one of: prompt, schema.

Tool id: hyperbrowser-api-extract
Provider: Hyperbrowser
Job: Extract api (api.extract)
Price: $0.02 per call. A call that fails at the provider costs $0.

Inputs

Name	Type	Required	Description
`maxLinks`	number	no
`prompt`	string	no	Example: “Extract the page title and main headline”
`schema`	object	no
`sessionOptions`	object	no
`systemPrompt`	string	no
`urls`	array	yes
`waitFor`	number	no

Output

The run’s result holds the provider’s answer. Signed in, looot inspect hyperbrowser-api-extract prints its fields.

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":"hyperbrowser-api-extract","input":{"urls":["https://stripe.com"],"prompt":"Extract the page title and main headline"},"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: "hyperbrowser-api-extract",
    input: {
      urls: ["https://stripe.com"],
      prompt: "Extract the page title and main headline",
    },
    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": "hyperbrowser-api-extract",
        "input": {
            "urls": ["https://stripe.com"],
            "prompt": "Extract the page title and main headline",
        },
        "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:api.extract as endpointId; see the job page.

Hyperbrowser API / Start an extract job

Inputs

Output

Run it