# Agent Fetch Hub — Web Extraction via x402

> Agent Fetch Hub — Web Extraction via x402 is a paid API for AI agents from fetch.netzhandwerker.de, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-14).

Fetches a URL and returns its content as clean Markdown, billed per-call in USDC over x402 with no API key required.

## Facts

- Endpoint: POST https://fetch.netzhandwerker.de/extract
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-fetch-hub-web-extraction-via-x402-e4824c94
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_O7V1_DTIWoTWyejjLxwl9

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 agent-fetch-hub-web-extraction-via-x402-e4824c94 -d '<json body>'
```

Example prompt: Fetch the webpage at https://example.com/article and give me the full content as clean Markdown, including any outbound links you find on the page.

## When to prefer this

Choose this endpoint when you need frictionless, pay-as-you-go web content extraction with no signup or API key overhead, especially in agentic pipelines where per-call micropayment via x402 is already supported. It is ideal for one-off or low-volume page fetches where a subscription-based scraping service would be overkill, and when clean Markdown output is the desired format for downstream LLM processing.

## Known failure modes

- URL is unreachable or returns a non-200 HTTP status — extraction fails with an error response
- URL points to a non-HTML resource (e.g. PDF, binary) that cannot be converted to Markdown
- Payment via x402 fails due to insufficient USDC balance — request is rejected with 402
- Page is behind authentication or a CAPTCHA wall — content cannot be extracted
- max_chars set too low — output is truncated and may omit important content
- Malformed or relative URL provided — endpoint returns a validation error

## How this service works

Fetch one URL and return clean article Markdown without navigation, ads or cookie banners.

## Output

Returns a JSON object containing the page content rendered as clean Markdown text, optionally including a list of outbound links found in the document and/or image references, truncated to max_chars if specified.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "description": "Absolute http or https URL to extract."
  },
  "format": {
   "enum": [
    "markdown",
    "text",
    "html"
   ],
   "type": "string",
   "default": "markdown"
  },
  "max_chars": {
   "type": "integer",
   "default": 200000,
   "maximum": 400000,
   "minimum": 500
  },
  "include_links": {
   "type": "boolean",
   "default": false,
   "description": "Return outbound links found in the document."
  },
  "include_images": {
   "type": "boolean",
   "default": false
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/article",
  "title": "Example article",
  "byline": "Jane Doe",
  "language": "en",
  "markdown": "# Example article\n\nFirst paragraph ...",
  "fetched_at": "2026-08-09T09:00:00Z",
  "word_count": 812
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-fetch-hub-web-extraction-via-x402-e4824c94/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from fetch.netzhandwerker.de](https://www.zero.xyz/host/fetch.netzhandwerker.de/llms.txt)