# Softbot Reader - Web Page to Markdown

> Softbot Reader - Web Page to Markdown is a paid API for AI agents from softbot-reader-mainnet.softbot.workers.dev, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-20).

Fetches a public web page and returns clean markdown content, page title, and metadata while respecting robots.txt

## Facts

- Endpoint: POST https://softbot-reader-mainnet.softbot.workers.dev/v1/read?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/softbot-reader-web-page-to-markdown-3b731ace
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_O0qvB73QdHfPWDndLGnjk

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 softbot-reader-web-page-to-markdown-3b731ace -d '<json body>'
```

Example prompt: Fetch the content of https://example.com/article and give me the full text as clean markdown so I can summarize it.

## When to prefer this

Choose this endpoint when you need a quick, clean markdown conversion of a single public web page — especially when you want readable prose extracted from HTML noise without running an LLM or parsing structured metadata. Prefer it over headless browsers or full crawlers when speed and simplicity matter and when robots.txt compliance is required.

## Known failure modes

- URL is blocked by robots.txt — endpoint refuses and returns an error
- Target URL is unreachable or returns a non-2xx HTTP status
- Malformed or non-HTTP/HTTPS URL provided
- Page is behind a login wall or JavaScript-heavy SPA that cannot be rendered
- Rate limit or payment failure prevents the request from completing

## How this service works

Fetch a public web page and return clean markdown, title and metadata. Respects robots.txt.

## Output

Returns clean markdown representation of the page body, the page title, and any available metadata (such as description or author) stripped of HTML noise; robots.txt is respected so inaccessible pages are refused

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "description": "Public http(s) URL to read"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/softbot-reader-web-page-to-markdown-3b731ace/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from softbot-reader-mainnet.softbot.workers.dev](https://www.zero.xyz/host/softbot-reader-mainnet.softbot.workers.dev/llms.txt)