# url2md

> url2md is a paid API for AI agents from bazaar.aiplan.one, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-29).

Fetches a URL and converts the page content to clean Markdown, stripping scripts, styles, and navigation while preserving text and links

## Facts

- Endpoint: GET https://bazaar.aiplan.one/api/v0/url2md?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/url2md-84451f55
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_osXcoFZVoe13TvQeliBa2

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 url2md-84451f55
```

Example prompt: Fetch the article at https://example.com/blog/my-post and give me the content as clean Markdown with all the navigation, scripts, and styling stripped out.

## When to prefer this

Use this endpoint when you need a lightweight, affordable ($0.001 per call) way to fetch and clean a single public URL into Markdown for downstream text processing, LLM summarization, or content extraction. Prefer this over full browser automation when the target page is primarily static HTML and you don't need structured data extraction or JavaScript rendering.

## Known failure modes

- URL is unreachable or returns a non-200 status — likely returns an error message
- URL is behind a login/paywall — only public content is accessible
- JavaScript-rendered pages may return incomplete content if the page requires client-side rendering
- Malformed or non-HTTPS URLs may be rejected by the input validation
- Very large pages may time out or return truncated content

## How this service works

URL → clean Markdown (strip scripts/styles/nav, keep text+links)

## Output

A clean Markdown representation of the target webpage's main content, with HTML scripts, stylesheets, navigation elements, and other boilerplate removed, while preserving the readable text and hyperlinks.

## 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": "https URL to convert"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/url2md-84451f55/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from bazaar.aiplan.one](https://www.zero.xyz/host/bazaar.aiplan.one/llms.txt)