# PennyRail Web Extract to Markdown

> PennyRail Web Extract to Markdown is a paid API for AI agents from pennyrail.vercel.app, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

Fetches a public URL and returns its main content as clean Markdown, stripping navigation and boilerplate using a browser-backed reader.

## Facts

- Endpoint: POST https://pennyrail.vercel.app/api/bazaar/web-extract
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pennyrail-web-extract-to-markdown-032b291b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_O2owbCuafsBJU_QkEitBq

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 pennyrail-web-extract-to-markdown-032b291b -d '<json body>'
```

Example prompt: Can you fetch the content from https://example.com/article and give me the main article text as clean markdown, without any navigation or sidebar clutter?

## When to prefer this

Use this endpoint when you need to retrieve and read the human-readable content of a public web page in a clean, agent-friendly markdown format. It is especially useful when the page requires JavaScript rendering (browser-backed) and when boilerplate stripping is important. Prefer it over raw HTTP fetch when you want the article body without navigation, ads, or sidebars.

## Known failure modes

- URL is behind a login wall or paywall — returns empty or partial content
- Page requires complex authentication or CAPTCHA — extraction may fail or return minimal content
- Invalid or unreachable URL — returns error response
- Page has no identifiable main content — may return raw or minimal markdown
- Rate limiting or blocking by target site — request may time out

## How this service works

Extract the useful content from a public URL as clean Markdown for agents. Uses a browser-backed reader when needed and strips navigation/boilerplate. Exact-match PennyRail gap-arbitrage route.

## Output

Returns the main textual content of the requested URL as clean Markdown, with navigation menus, ads, footers, and other boilerplate removed. Uses a browser-backed rendering step when JavaScript execution is needed to load the page content.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "type": "object",
     "description": "Input for Web page extract to Markdown.",
     "additionalProperties": true
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pennyrail-web-extract-to-markdown-032b291b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from pennyrail.vercel.app](https://www.zero.xyz/host/pennyrail.vercel.app/llms.txt)