Firecrawl: Extract

Extract structured data from web page URLs or websites with an AI prompt and a JSON schema, as an asynchronous job.

Tool ID: firecrawl_extract

Run this action

Use the TypeScript SDK for a single call. Put ctx.tools.execute(...) inside a Play when the call should be durable, scheduled, or run across a CSV.

import { Deepline } from 'deepline';

const deepline = await Deepline.connect();
const result = await deepline.tools.execute(
  'firecrawl_extract',
  {
    "urls": [
      "https://example.com"
    ]
  },
);

console.log(result.toolResponse.raw);

CLI

deepline tools execute firecrawl_extract --input '{
  "urls": [
    "https://example.com"
  ]
}' --json

Example response

The SDK exposes this shape at result.toolResponse.raw. Values below are representative.

{
  "data": {
    "status": "example"
  }
}

Use deepline tools get firecrawl_extract --json for the latest machine-readable contract.

Input reference

Start an extraction job and return its ID for status polling.

Name	Type	Required	Default	Details
`payload.urls`	`array`	Yes	—	URLs to extract data from
`payload.prompt`	`string`	No	—	Natural language extraction instructions
`payload.schema`	`record`	No	—	JSON schema for structured output
`payload.enableWebSearch`	`boolean`	No	—	Enable web search to augment extraction
`payload.ignoreSitemap`	`boolean`	No	—	Ignore sitemap when discovering pages (default false)
`payload.includeSubdomains`	`boolean`	No	—	Include subdomains in extraction (default true)
`payload.showSources`	`boolean`	No	—	Include source URLs in response (default false)
`payload.ignoreInvalidURLs`	`boolean`	No	—	Skip invalid URLs instead of failing (default true)
`payload.scrapeOptions`	`object`	No	—	Scrape options for each URL
`payload.timeoutMs`	`integer`	No	—	Deprecated compatibility field. Start actions now return immediately; use the matching status action to poll.

This input schema is too large to embed without slowing the page. Get the complete live contract with deepline tools get firecrawl_extract --json.

Output reference

Structured extraction result.

Name	Type	Required	Default	Details
`result.data`	`object`	Yes	—	Provider response payload.
`result.data.id`	`string`	No	—	—
`result.data.status`	`string`	Yes	—	—
`result.data.data`	`unknown`	No	—	—
`result.data.tokensUsed`	`number`	No	—	—
`result.data.expiresAt`	`string`	No	—	—
`result.meta`	`record`	No	—	Additional response metadata (status, paging).

Deepline cost

Pricing model: provider_usage (provider usage).
Estimated Deepline credits: 0 per pricing unit.

Get started

Build and automate

Common workflows

Data and integrations

Reference

Firecrawl: Extract

Run this action

CLI

Example response

Input reference

Output reference

Deepline cost

​Run this action

​CLI

​Example response

​Input reference

​Output reference

​Deepline cost

​Related documentation

Run this action

CLI

Example response

Input reference

Output reference

Deepline cost

Related documentation