POST/v1/extract

Extract

Extract structured data from web pages or raw content using LLM. Accepts URLs to scrape first, or raw markdown/HTML content directly. Returns typed JSON matching your schema.

Target Latency

1.2s - 4.5s

Credits

5 cr/req

Parameters

Name	Type	Requirement	Description
url	string	optional	Single URL to scrape then extract from.
urls	string[]	optional	Multiple URLs to scrape and extract from (async job).
content	string	optional	Raw markdown/text content to extract from (no scraping needed).
html	string	optional	Raw HTML to convert and extract from.
prompt	string	optional	Natural language extraction instruction (e.g. 'Extract all product names and prices').
schema	object	optional	JSON Schema for structured output. The LLM will return data matching this schema.
provider	string	optional	LLM provider: "openai", "anthropic", "groq", etc.
only_main_content	boolean	optional	Extract only main content before LLM processing.
wait_for	number	optional	Wait ms after page load (for URLs).
timeout	number	optional	Scrape timeout in ms (for URLs).
use_proxy	boolean	optional	Use proxy for scraping.
headers	object	optional	Custom HTTP headers.
cookies	object	optional	Custom cookies.
webhook_url	string	optional	Webhook URL for extraction completion notification.
webhook_secret	string	optional	HMAC secret for webhook signature verification.

cURL Example

curl -X POST "https://api.datablue.dev/v1/extract" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "url": "https://openai.com/pricing",
  "prompt": "Extract all pricing tiers with name, price per million tokens, and context window",
  "schema": {
    "type": "object",
    "properties": {
      "tiers": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "name": {
              "type": "string"
            },
            "input_price": {
              "type": "string"
            },
            "output_price": {
              "type": "string"
            },
            "context_window": {
              "type": "string"
            }
          }
        }
      }
    }
  }
}'

System Responses

200 OK

Request processed successfully.

401 UNAUTHORIZED

Missing or invalid API key.

429 RATE LIMIT

System capacity exceeded.

500 SYSTEM FAILURE

Internal core exception.

EXAMPLE RESPONSE

{
  "success": true,
  "data": {
    "url": "https://openai.com/pricing",
    "extract": {
      "tiers": [
        {
          "name": "GPT-4o",
          "input_price": "$2.50/1M",
          "output_price": "$10.00/1M",
          "context_window": "128K"
        },
        {
          "name": "GPT-4o mini",
          "input_price": "$0.15/1M",
          "output_price": "$0.60/1M",
          "context_window": "128K"
        },
        {
          "name": "GPT-4.1",
          "input_price": "$2.00/1M",
          "output_price": "$8.00/1M",
          "context_window": "1M"
        }
      ]
    },
    "content_length": 48230
  }
}