# Cerwal Web Extract

> Cerwal Web Extract is a paid API for AI agents from cerwal.vercel.app, paid per call via x402, $0.25/call, status unknown (last checked 2026-09-14).

Scrapes and extracts content from a given URL, paid per-request in USDC via x402 with no authentication required

## Facts

- Endpoint: POST https://cerwal.vercel.app/api/extract
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/cerwal-web-extract-c10fb763
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_duN7x0aoGNO-nh9V3qAtq

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 cerwal-web-extract-c10fb763 -d '<json body>'
```

Example prompt: Can you scrape the content from https://example.com/article and pull out whatever data is on that page?

## When to prefer this

Choose this endpoint when you need a simple, no-auth, pay-per-use web scraping solution for AI agents, especially when you want to avoid subscription overhead and only pay $0.25 USDC per call via x402. Best for ad-hoc or low-volume URL extraction tasks where setting up a scraping infrastructure or managing API keys is not desirable.

## Known failure modes

- Invalid or unreachable URL returns success:false
- Target website blocks scraping bots (403/429 responses)
- Payment failure via x402 prevents request from completing
- Malformed URL input causes request rejection
- Dynamic JavaScript-heavy pages may return incomplete content if not rendered
- Timeout on slow-loading pages

## How this service works

Web scraping and search for AI agents. No auth, no subscriptions. Pay per request in USDC via x402.

## Output

Returns a JSON object with a 'success' boolean indicating whether the extraction succeeded, and a 'data' object containing the scraped and extracted content from the target URL.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "url"
 ],
 "properties": {
  "url": {
   "type": "string",
   "description": "URL to extract from"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "object"
  },
  "success": {
   "type": "boolean"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/cerwal-web-extract-c10fb763/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from cerwal.vercel.app](https://www.zero.xyz/host/cerwal.vercel.app/llms.txt)