# AMNT Fetch & Read – Web Page to Markdown

> AMNT Fetch & Read – Web Page to Markdown is a paid API for AI agents from www.amnt.io, paid per call via x402, $0.004/call, status unknown (last checked 2026-09-15).

Fetches any public web page and converts it into clean, readable markdown that an AI agent can process

## Facts

- Endpoint: POST https://www.amnt.io/api/os-tools/fetch-read
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/amnt-fetch-read-web-page-to-markdown-36650351
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_BQZlGxcQakeX_Cnmz_y9p

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 amnt-fetch-read-web-page-to-markdown-36650351 -d '<json body>'
```

Example prompt: Can you fetch the article at https://www.wired.com/story/ai-agents-future and turn it into clean markdown so I can read it? Keep the links in and cut it off at 30000 characters if it's too long.

## When to prefer this

Choose this endpoint when you need a clean, LLM-readable text representation of any public web page without writing custom scraping logic. It is ideal for agents that need to read articles, documentation, or landing pages on demand without managing HTML parsing. Prefer it over raw HTTP fetches when your agent needs prose-ready content with optional link preservation and a configurable length cap.

## Known failure modes

- Non-public or paywalled URLs return empty or partial content
- Invalid or malformed URLs cause a request error
- Pages heavily reliant on JavaScript rendering may return incomplete markdown
- maxChars set below 500 or above 100000 are rejected with validation error
- Timeout on very slow or unresponsive servers
- Private or localhost URLs may be blocked for security reasons

## How this service works

Fetch and Read - Turn any web page into clean markdown an agent can actually read.

## Output

Returns a markdown-formatted string of the page's readable content, with optional hyperlinks preserved in [text](url) format. The response indicates whether the content was truncated at the requested character limit, allowing the agent to know if the full page was returned or cut short.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "examples": [
    "https://example.com/article"
   ],
   "maxLength": 2000,
   "description": "The public https page to read."
  },
  "maxChars": {
   "type": "integer",
   "default": 20000,
   "maximum": 100000,
   "minimum": 500,
   "description": "Cut the markdown at this length. The reply says whether it was cut."
  },
  "includeLinks": {
   "type": "boolean",
   "default": true,
   "description": "Keep [text](url) links in the markdown. Turn off for prose only."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/amnt-fetch-read-web-page-to-markdown-36650351/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from www.amnt.io](https://www.zero.xyz/host/www.amnt.io/llms.txt)