# Soren Web Page Reader

> Soren Web Page Reader is a paid API for AI agents from soren.com, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-14).

Fetches any public URL and returns its content as clean, boilerplate-stripped markdown ready for an LLM context window

## Facts

- Endpoint: GET https://soren.com/v1/web/read
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/soren-web-page-reader-1eba7453
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-ZlXJVmhwYAfDBv3X-5PU

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 soren-web-page-reader-1eba7453
```

Example prompt: Can you read the content of https://techcrunch.com/2024/01/15/openai-announcement/ and give me a clean summary — use stealth mode since TechCrunch tends to block bots?

## When to prefer this

Choose this endpoint when your agent needs the full text content of a specific known URL and you don't want to maintain a scraping stack. It's ideal for one-off URL reads, article extraction, and documentation fetching. Use stealth=true ($0.05) for sites with aggressive bot protection. Pair with /v1/web/search when you need to discover URLs first. Prefer this over maintaining your own headless browser infrastructure for occasional page reads.

## Known failure modes

- URL is unreachable or returns a non-200 status — no charge, returns failed fetch indicator
- URL is behind a hard paywall requiring authentication — content may be incomplete
- stealth=false on an aggressively bot-protected site may return blocked/empty content
- Malformed or non-HTTP(S) URL returns a validation error
- Very large pages may be truncated to fit context window limits

## How this service works

Read any public web page as clean markdown — rendered, boilerplate stripped, ready for a context window. Use it when your agent needs the content of a URL and has a wallet instead of a scraping stack. Charged ONLY if the fetch succeeds; a failed fetch costs nothing. stealth=true ($0.05) gets past aggressive bot protection. Pair with /v1/web/search to find pages first.

## Output

Clean markdown representation of the fetched web page, with navigation menus, ads, headers, footers and other boilerplate stripped out — leaving only the main readable content, ready to be inserted into an LLM context window.

## Request schema (JSON Schema)

```json
{
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "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",
       "examples": [
        "https://example.com/article"
       ],
       "description": "Public http(s) URL to read."
      },
      "stealth": {
       "type": "string",
       "examples": [
        "false"
       ],
       "description": "true routes through stealth proxying for protected sites. Price becomes $0.05."
      }
     }
    }
   },
   "additionalProperties": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/soren-web-page-reader-1eba7453/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from soren.com](https://www.zero.xyz/host/soren.com/llms.txt)