# spipe Content Extraction API

> spipe Content Extraction API is a paid API for AI agents from spip39.vercel.app, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-11).

Extracts and returns the text/content of one or more web URLs, with configurable output formats and crawl timeout.

## Facts

- Endpoint: POST https://spip39.vercel.app/contents?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/spipe-content-extraction-api-85196a3a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_GWujCEmxfESUGvD8kkJhM

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-extraction-api-85196a3a -d '<json body>'
```

Example prompt: Pull the full text content from these three URLs — https://example.com/article1, https://example.com/article2, and https://example.com/article3 — and give me 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 one or more specific URLs and have the URLs in hand. It is well-suited for AI agent research pipelines where multiple pages need to be fetched in a single call with configurable timeout. Prefer it over general search endpoints when you already know the target URLs and just need their content.

## Known failure modes

- URL is unreachable or returns a non-200 HTTP status — content may be missing or errored for that URL
- Crawl timeout exceeded for a slow-loading page — partial or no content returned
- URL points to a JavaScript-heavy SPA that cannot be statically extracted — empty or incomplete content
- Invalid URL format in the urls array — request validation error
- Payment failure via x402 — 402 response, content not returned

## How this service works

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

## Output

A JSON object containing the extracted content from each requested URL, potentially including the page text in the requested format (e.g. markdown or plain text). The exact response structure is generic but includes the fetched content per URL.

## 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-extraction-api-85196a3a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from spip39.vercel.app](https://www.zero.xyz/host/spip39.vercel.app/llms.txt)