Document Extraction API | Unified Agent APIs

Overview

Extract structured data from URLs or content

Credits

3 credits per call

Providers

FirecrawlClaude

SDK Method

client.documents.find(...)

Parameters

url

string

URL to scrape and extract from.

content

string

Pre-scraped text content.

extraction_prompt

string

What to extract.

schema

string

JSON schema for extraction.

Example Response

{
  "success": true,
  "data": {
    "extracted": {
      "main_heading": "Example Domain",
      "links": [
        {
          "text": "Learn more",
          "url": "https://iana.org/domains/example"
        }
      ]
    },
    "source_url": "https://example.com",
    "content_length": 167,
    "truncated": false
  },
  "metadata": {
    "provider_used": "llm_extraction",
    "providers_tried": [
      "llm_extraction"
    ],
    "mode_used": null,
    "response_time_ms": 1716,
    "request_id": "req_bc82d469"
  },
  "credits_used": 3
}

Get Started

Use this API through the O-mega platform. Create an API key in your dashboard, then call the endpoint with your key in the Authorization header.

Try Document Extraction

Test Document Extraction in the interactive playground. No setup required.

Open Playground