# fetchwerk Web Extraction – Single URL

> fetchwerk Web Extraction – Single URL is a paid API for AI agents from fetch.halowerk.com, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-15).

Fetches a single URL and returns its main content as clean Markdown, plain text, or HTML, stripping navigation, ads, and cookie banners.

## Facts

- Endpoint: POST https://fetch.halowerk.com/extract
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/fetchwerk-web-extraction-single-url-6bd0b809
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_zaepB-tHS8ZXNtwgA72Ez

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 fetchwerk-web-extraction-single-url-6bd0b809 -d '<json body>'
```

Example prompt: Can you fetch the article at https://example.com/article/why-ai-matters and give me the main content as clean markdown, skipping any ads or navigation?

## When to prefer this

Choose this endpoint when you need to read and clean a single known URL — especially for article text, blog posts, documentation pages, or any page where you want human-readable content free of navigation and ads. It is the lowest-cost, lowest-friction option when you have exactly one URL and want markdown output. Prefer the batch sibling endpoint when processing multiple URLs in one call, or the structured-data sibling endpoints when you need product prices, metadata, or schema-filled fields.

## Known failure modes

- URL is unreachable or returns a non-200 status — extraction fails with an error
- Paywalled or login-required pages return only visible teaser content or nothing
- Dynamic JavaScript-heavy pages may not render fully, resulting in incomplete content
- max_chars too small to capture meaningful content (minimum 500)
- Malformed or non-HTTP/HTTPS URLs are rejected by input validation

## How this service works

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

## Output

A clean representation of the page's main content in the requested format (markdown by default, or plain text or HTML), trimmed to the specified character limit. Optionally includes a list of outbound links and images found in the document. Navigation, ads, cookie banners, and boilerplate are removed.

## 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
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/fetchwerk-web-extraction-single-url-6bd0b809/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from fetch.halowerk.com](https://www.zero.xyz/host/fetch.halowerk.com/llms.txt)