# Agent Tools HTML-to-Markdown Converter

> Agent Tools HTML-to-Markdown Converter is a paid API for AI agents from agent-tools-x402.t6y11a.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-31).

Converts raw HTML into clean Markdown, extracting title, excerpt, and formatted body text.

## Facts

- Endpoint: POST https://agent-tools-x402.t6y11a.workers.dev/api/markdown?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-31
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-tools-html-to-markdown-converter-6237b2c1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_4qlc_KxnrqznOGywG2Xil

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 agent-tools-html-to-markdown-converter-6237b2c1 -d '<json body>'
```

Example prompt: I have the raw HTML of a blog article — can you convert it to clean Markdown and pull out the title and a short excerpt? The page's original URL is https://example.com/blog/my-post so links resolve correctly.

## When to prefer this

Choose this endpoint when you already hold raw HTML and need a clean Markdown representation without making any additional network requests. It is ideal for post-scrape processing pipelines where an agent has fetched a page and now needs structured, LLM-friendly text. Prefer it over generic HTML strippers when you also need a title and excerpt alongside the Markdown body. Note: the service does not fetch URLs itself — you must supply the HTML directly.

## Known failure modes

- HTML exceeds 1 million character limit — request rejected
- Malformed or empty HTML input — may return empty markdown fields
- No recognisable article structure in HTML — title and excerpt may be empty strings
- Network or worker timeout for very large HTML payloads
- Payment failure via x402 — request not charged and not processed

## How this service works

Pay-per-call utilities for AI agents. Payments in USDC on Base via x402 v2; no accounts or API keys. Failed requests are never charged. No endpoint performs server-side fetching of caller-supplied URLs.

## Output

A JSON object containing the page title, a short excerpt summary, the full page body rendered as Markdown, and the total character count of the Markdown output.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "optional source URL used as link base"
  },
  "html": {
   "type": "string",
   "description": "raw HTML of the page (max 1M chars)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "title": "Example article",
  "excerpt": "A short summary",
  "markdown": "# Example article\n\nBody text...",
  "markdownChars": 1204
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-tools-html-to-markdown-converter-6237b2c1/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-tools-x402.t6y11a.workers.dev](https://www.zero.xyz/host/agent-tools-x402.t6y11a.workers.dev/llms.txt)