# spipe Content Extractor

> spipe Content Extractor is a paid API for AI agents from spip31.vercel.app, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-23).

Extracts and returns readable content from one or more URLs, with configurable output formats and per-page crawl timeout.

## Facts

- Endpoint: POST https://spip31.vercel.app/contents?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/spipe-content-extractor-6610a45e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_4gYlov3bS0nCXtPA4Af0h

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 spipe-content-extractor-6610a45e -d '<json body>'
```

Example prompt: Can you extract the full readable content from these three URLs — https://example.com/article1, https://example.com/article2, and https://example.com/article3 — and return the results in markdown format with a 30-second timeout per page?

## When to prefer this

Choose this endpoint when you need to extract readable content from multiple URLs in a single call, particularly when you want configurable output formats (e.g. markdown) and per-page timeout control. It is well-suited for batch web research pipelines where an AI agent needs to ingest web content programmatically. Prefer this over single-URL scrapers when handling lists of pages, and over full-site crawlers when you already know the specific URLs to target.

## Known failure modes

- URL is unreachable or returns a non-200 status — content not returned for that URL
- Crawl timeout exceeded for a page — partial or no content returned for slow-loading pages
- Invalid URL format in the urls array — request may fail or skip that entry
- Payment not fulfilled via x402 on Base — 402 response returned before content is served
- Unsupported output format specified — may return an error or fallback format

## How this service works

Web search, content extraction, and research APIs for AI agents. x402 on Base.

## Output

Returns a JSON object containing the extracted content from each provided URL, delivered in the requested output format (e.g. markdown, plain text). The response includes parsed readable content per URL, enabling downstream summarization, analysis, or storage by the calling agent.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "urls"
 ],
 "properties": {
  "urls": {
   "type": "array",
   "description": "URLs to extract"
  },
  "formats": {
   "type": "array",
   "description": "Output formats"
  },
  "crawl_timeout": {
   "type": "integer",
   "description": "Timeout per page (1-60s)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/spipe-content-extractor-6610a45e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from spip31.vercel.app](https://www.zero.xyz/host/spip31.vercel.app/llms.txt)