# Superhighway Web Page Reader

> Superhighway Web Page Reader is a paid API for AI agents from sh-origin.walls.sh, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-15).

Fetches any web page URL and returns clean, readable markdown and plain text content extracted from the HTML, ready for AI agent consumption.

## Facts

- Endpoint: GET https://sh-origin.walls.sh/scrape
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/superhighway-web-page-reader-e69cce42
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UB0lkGOgUydyGeqj6wiV2

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 superhighway-web-page-reader-e69cce42
```

Example prompt: Can you read the page at https://example.com/some-article and give me the main content as clean text so I can work with it?

## When to prefer this

Choose this endpoint when your agent needs to read and understand the textual content of a specific web page URL — especially for feeding content into RAG, summarizing articles, reading documentation, or accessing pages that need clean text extraction. It is pay-per-call with no signup required (USDC via x402), making it ideal for agentic workflows that need on-demand web reading without managing API keys. Prefer this over a search endpoint when you already have the URL and need the full page content rather than just a snippet.

## Known failure modes

- URL is unreachable or returns a non-200 HTTP status — empty or error response returned
- Page is behind a login or paywall — only publicly accessible content can be extracted
- JavaScript-heavy single-page apps may render incompletely if content is not in initial HTML
- Invalid or malformed URL input causes a request failure
- Rate limiting or blocking by the target website may result in empty content

## How this service works

Read any web page as clean text + markdown for AI agents. Give a URL, get back the page title, readable markdown, and plain text — the readable content extracted from the HTML. Pay-per-call in USDC via x402 — no signup, no API key. Use for letting an agent read pages, fetch articles/docs it can't access, scrape content, and feed RAG.

## Output

Returns the page title, the full readable content as clean markdown, and a plain text version — HTML boilerplate, navigation, ads, and other noise stripped out. Structured for immediate use by an AI agent or RAG ingestion pipeline.

## 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"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "The page URL to read (http/https)."
      }
     }
    }
   },
   "additionalProperties": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/superhighway-web-page-reader-e69cce42/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sh-origin.walls.sh](https://www.zero.xyz/host/sh-origin.walls.sh/llms.txt)