Firecrawl API / Extract structured data from pages using LLMs

Firecrawl tool firecrawl-extract on looot: input fields, $0.000333 per result, output shape, and code to run it with curl, JavaScript or Python.

Extracts structured data from one or more pages with an LLM. Send urls (up to 100). Priced from Firecrawl’s reported credits, which grow with page size.

Tool id: firecrawl-extract
Provider: Firecrawl
Job: Schema web extract (web.extract.schema)
Price: $0.000333 per result. A call that fails at the provider costs $0.

Inputs

Name	Type	Required	Description
`enableWebSearch`	boolean	no	When true, the extraction will use web search to find additional data
`ignoreInvalidURLs`	boolean	no	If invalid URLs are specified in the urls array, they will be ignored. Instead of them failing the entire request, an extract using the remaining valid URLs will be performed, and the invalid URLs will be returned in the invalidURLs field of the response.
`ignoreSitemap`	boolean	no	When true, sitemap.xml files will be ignored during website scanning
`includeSubdomains`	boolean	no	When true, subdomains of the provided URLs will also be scanned
`prompt`	string	no	Prompt to guide the extraction process
`schema`	string	no	Schema to define the structure of the extracted data. Must conform to JSON Schema.
`scrapeOptions`	string	no
`showSources`	boolean	no	When true, the sources used to extract the data will be included in the response as `sources` key
`urls`	array	yes

Output

Shape of the run’s result, checked against 1 real answer:

{ data: { pageTitle }, status, success, warnings: string[], expiresAt, tokensUsed, creditsUsed, replacement }

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":"firecrawl-extract","input":{"urls":[]},"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: "firecrawl-extract",
    input: {
      urls: [],
    },
    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": "firecrawl-extract",
        "input": {
            "urls": [],
        },
        "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.extract.schema as endpointId; see the job page.

Firecrawl API / Extract structured data from pages using LLMs

Inputs

Output

Run it