# AgentFeed Web Page to Markdown

> AgentFeed Web Page to Markdown is a paid API for AI agents from x402.ochinimus.app, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-14).

Fetches a single web page URL and returns its main content as clean markdown, using Mozilla Readability and Turndown for extraction.

## Facts

- Endpoint: GET https://x402.ochinimus.app/api/web-markdown?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentfeed-web-page-to-markdown-97778fb9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UBT9Dz-cdTmuCfLl_M93Z

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 agentfeed-web-page-to-markdown-97778fb9
```

Example prompt: Can you fetch the content of https://www.bbc.com/news/technology-12345678 and give me the main article text as clean markdown?

## When to prefer this

Use this endpoint when you need to retrieve and read the human-readable main content of a single web page as clean markdown, stripping away navigation, ads, and boilerplate. It is ideal for article reading, content extraction for summarization, or verifying what a page currently says. Prefer it over raw HTML fetchers when you want structured, readable output without post-processing. It respects robots.txt and refuses private addresses, making it suitable for production agent workflows. Not suitable for crawling multiple pages or extracting structured data beyond the main article body.

## Known failure modes

- URL is blocked by robots.txt — returns an error, no charge
- URL points to a private/local IP address — refused for security
- Page exceeds 5 MB limit — content is truncated, truncated flag set to true
- Fetch timeout after 10 seconds — returns an error, no charge
- Non-HTTP/HTTPS scheme or non-standard port — rejected
- URL is unreachable or returns a non-200 status — returns an error, no charge

## How this service works

Web page to markdown: the main content of the one URL you pass as clean markdown (Mozilla Readability, then turndown), with title, final URL, fetch time and word count. http or https on ports 80 and 443, 5 MB, 10 s; robots.txt honoured and private addresses refused. Use when you need to answer: What does this web page say, as clean markdown? A blocked or unreachable URL is never charged.

## Output

A JSON object containing: the extracted main content as markdown, the page title, byline, site name, language, final (redirected) URL, fetch timestamp, word count, a truncation flag indicating if the content was cut off at 5 MB, and the extraction method used (Readability or fallback). Blocked or unreachable URLs are not charged.

## 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 to convert: an absolute http or https URL"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "data": {
       "type": "object",
       "properties": {
        "url": {
         "type": "string"
        },
        "lang": {
         "type": "string"
        },
        "title": {
         "type": "string"
        },
        "byline": {
         "type": "string"
        },
        "rights": {
         "type": "string"
        },
        "markdown": {
         "type": "string"
        },
        "final_url": {
         "type": "string"
        },
        "site_name": {
         "type": "string"
        },
        "truncated": {
         "type": "boolean"
        },
        "extraction": {
         "type": "string"
        },
        "fetched_at": {
         "type": "string"
        },
        "word_count": {
         "type": "number"
        }
       }
      },
      "paid": {
       "type": "boolean"
      },
      "tool": {
       "type": "string"
      }
     }
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentfeed-web-page-to-markdown-97778fb9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.ochinimus.app](https://www.zero.xyz/host/x402.ochinimus.app/llms.txt)