# fetchwerk Batch Web Extraction

> fetchwerk Batch Web Extraction is a paid API for AI agents from fetch.halowerk.com, paid per call via x402, $0.008/call, status unknown (last checked 2026-09-14).

Fetches and extracts clean content from up to 10 URLs in a single paid API call, returning markdown, plain text, or HTML.

## Facts

- Endpoint: POST https://fetch.halowerk.com/batch/extract
- Price: $0.008/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/fetchwerk-batch-web-extraction-443208a0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_0vBqLtfLHeggbG3pSvfsK

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-batch-web-extraction-443208a0 -d '<json body>'
```

Example prompt: Can you fetch the content from these 5 URLs for me and return everything as clean markdown — cap each page at 100,000 characters: https://example.com/page1, https://example.com/page2, https://example.com/page3, https://example.com/page4, https://example.com/page5?

## When to prefer this

Choose this endpoint when you need to extract clean readable content from multiple URLs (2–10) in a single call, reducing round-trips and cost compared to fetching each URL individually. Ideal for bulk research, competitive analysis, or content aggregation tasks where you control the list of URLs upfront. Prefer this over the single-URL sibling endpoint when you have a batch of pages to process simultaneously.

## Known failure modes

- One or more URLs are unreachable or return non-200 status (partial results or per-URL error)
- URLs exceed the maxItems limit of 10 (validation error)
- max_chars outside allowed range 500–400000 (validation error)
- Paywalled or JavaScript-heavy pages may return incomplete content
- Payment failure via x402 protocol blocks the entire batch call

## How this service works

Extract up to ten URLs in one paid call.

## Output

Returns extracted page content for each submitted URL in the requested format (markdown, plain text, or HTML), stripped of navigation, ads, and other clutter, up to the specified character limit per page.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "urls": {
   "type": "array",
   "items": {
    "type": "string",
    "format": "uri"
   },
   "maxItems": 10,
   "minItems": 1
  },
  "format": {
   "enum": [
    "markdown",
    "text",
    "html"
   ],
   "type": "string",
   "default": "markdown"
  },
  "max_chars": {
   "type": "integer",
   "default": 200000,
   "maximum": 400000,
   "minimum": 500
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/fetchwerk-batch-web-extraction-443208a0/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)