# Tarnak x402 URL-to-Markdown Extractor

> Tarnak x402 URL-to-Markdown Extractor is a paid API for AI agents from api.capousd-student-tools.me, paid per call via x402, $0.004/call, status unknown (last checked 2026-10-31).

Fetches a URL or raw HTML and converts it to clean, structured Markdown with metadata extraction

## Facts

- Endpoint: POST https://api.capousd-student-tools.me/v1/extract?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-31
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tarnak-x402-url-to-markdown-extractor-b1882079
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Yu3bExf-UaybwKWnVidJu

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 tarnak-x402-url-to-markdown-extractor-b1882079 -d '<json body>'
```

Example prompt: Can you fetch the article at https://example.com/article and convert it to clean markdown so I can read the body text and see the author and description?

## When to prefer this

Choose this endpoint when you need a keyless, pay-per-call web content extraction service that returns clean Markdown with metadata — ideal for AI agent pipelines on Base that want to avoid API key management overhead and pay micro-amounts per call via USDC x402 protocol.

## Known failure modes

- URL is unreachable or returns non-200 status — may return an error or empty markdown
- Paywalled or JavaScript-rendered pages may return incomplete or no content
- Malformed HTML input may produce garbled markdown output
- Rate limit exceeded beyond 10 free verdicts per IP per day without payment
- x402 payment not completed — endpoint returns 402 and no content

## How this service works

Keyless pay-per-call APIs for AI agents on Base: token risk verdict, rug/honeypot report, gas estimate, URL-to-markdown and more. x402 v2, USDC, no API key or signup. 10 free verdicts per IP per day.

## Output

A JSON object containing the source URL, extracted page title, metadata fields (author, description), and the full cleaned body text converted to Markdown format.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "URL to fetch and convert."
  },
  "html": {
   "type": "string",
   "description": "Raw HTML instead of a URL."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/article",
  "meta": {
   "author": "Example",
   "description": "Example description"
  },
  "title": "Example article",
  "markdown": "# Example article\n\nCleaned body text."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tarnak-x402-url-to-markdown-extractor-b1882079/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.capousd-student-tools.me](https://www.zero.xyz/host/api.capousd-student-tools.me/llms.txt)