# ScrapeGraphAI Search & Extract

> ScrapeGraphAI Search & Extract is a paid API for AI agents from x402.orthogonal.com, paid per call via x402, $0.03/call, status unknown (last checked 2026-09-15).

Runs a web search, scrapes the top N result URLs, and optionally applies LLM extraction with a custom prompt and JSON schema to return structured data.

## Facts

- Endpoint: POST https://x402.orthogonal.com/scrapegraphai/api/search
- Price: $0.03/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/scrapegraphai-search-extract-9cdb23fd
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_VOSLdksx6f-bw1WQKRH9l

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-search-extract-9cdb23fd -d '<json body>'
```

Example prompt: Search for 'best electric SUVs 2024' and scrape the top 5 results, then extract the car model name, price range, and range in miles from each page as structured JSON.

## When to prefer this

Choose this endpoint when you need to both search the web AND extract structured data from the results in a single call — especially when you want LLM-driven extraction with a custom schema. It outperforms simple search endpoints when downstream structured data (not raw text) is required, and beats single-URL scrapers when you need multi-source aggregation from a query.

## Known failure modes

- Query too vague returns low-quality or irrelevant scraped pages
- Target URLs may block scraping and return empty or partial content
- LLM extraction may fail to match provided schema if page content is sparse
- timeRange filter may return no results for niche queries
- numResults capped at 20; very broad queries may still miss relevant sources
- Schema mismatch between expected and extracted fields results in null values

## How this service works

Runs a search, scrapes the top N result URLs, optionally runs LLM extraction with prompt and schema.

## Output

Returns scraped content from the top N search result URLs in markdown or HTML format. If a prompt and schema are provided, also returns LLM-extracted structured JSON matching the schema, derived from the scraped content.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "mode": {
   "type": "string",
   "description": "Content mode: normal, reader, or prune (default prune)"
  },
  "query": {
   "type": "string",
   "description": "Search query (1-500 chars)"
  },
  "format": {
   "type": "string",
   "description": "Output format: html or markdown (default markdown)"
  },
  "prompt": {
   "type": "string",
   "description": "LLM extraction prompt (1-10000 chars)"
  },
  "schema": {
   "type": "object",
   "description": "JSON schema for structured extraction"
  },
  "timeRange": {
   "type": "string",
   "description": "Time filter: past_hour, past_24_hours, past_week, past_month, past_year"
  },
  "numResults": {
   "type": "number",
   "description": "Number of results to scrape (1-20, default 3)"
  },
  "fetchConfig": {
   "type": "object",
   "description": "Fetch options"
  },
  "locationGeoCode": {
   "type": "string",
   "description": "Geo code for location-based results (max 10 chars)"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/scrapegraphai-search-extract-9cdb23fd/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.orthogonal.com](https://www.zero.xyz/host/x402.orthogonal.com/llms.txt)