# ScrapeGraphAI Extract

> ScrapeGraphAI Extract is a paid API for AI agents from ScrapeGraphAI at mpp.orthogonal.com, paid per call via MPP, $0.025/call (dynamic — varies by input), status unknown (last checked 2026-10-10).

Uses LLMs to extract structured data from a URL, HTML, or markdown input given a natural language prompt and optional JSON schema.

## Facts

- Endpoint: POST https://mpp.orthogonal.com/scrapegraphai/api/extract?utm_source=zero.xyz
- Price: $0.025/call (dynamic — varies by input)
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Provider: ScrapeGraphAI
- Docs: https://v2-api.scrapegraphai.com
- Website: https://v2-api.scrapegraphai.com
- Tags: scraping, extraction, llm, crawl, web, data
- Canonical page: https://www.zero.xyz/c/scrapegraphai-extract-70df0311
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_x9P-ki9GIeiLYB7L98eic

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability scrapegraphai-extract-70df0311 -d '<json body>'
```

Example prompt: Extract the product name, price, and availability from this URL — https://example.com/product/123 — and return it as JSON with fields: name, price, and in_stock.

## When to prefer this

Use this endpoint when you need LLM-powered, schema-driven extraction from a specific URL or raw HTML/markdown — especially when the target data is unstructured or requires semantic understanding rather than CSS selectors or XPath. Prefer this over generic scraping when you want typed, validated JSON output matching a custom schema.

## Known failure modes

- URL is inaccessible or returns non-200 status
- HTML/markdown input is malformed or too large
- LLM fails to map content to the provided JSON schema
- Schema fields cannot be found in the source content, returning nulls
- Rate limit exceeded or insufficient USDC balance
- Prompt is too vague to produce deterministic extraction

## How this service works

LLM-driven extraction from a URL, HTML, or markdown input with a prompt and optional JSON schema.

## Output

Returns a structured JSON object containing the fields requested in the prompt and schema, extracted from the provided URL, HTML, or markdown content using LLM-driven parsing.

## Example request

```json
{
 "html": "<html><head><title>Sample Product</title></head><body><div class='product'><h1>Wireless Bluetooth Headphones</h1><span class='price'>$79.99</span><p class='availability'>In Stock</p></div></body></html>",
 "prompt": "Extract the product name, price, and stock status",
 "schema": {
  "type": "object",
  "required": [
   "name",
   "price",
   "in_stock"
  ],
  "properties": {
   "name": {
    "type": "string",
    "description": "Product name"
   },
   "price": {
    "type": "string",
    "description": "Product price"
   },
   "in_stock": {
    "type": "boolean",
    "description": "Whether the product is in stock"
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/scrapegraphai-extract-70df0311/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mpp.orthogonal.com](https://www.zero.xyz/host/mpp.orthogonal.com/llms.txt)