# AgentReader HTML to Markdown Converter

> AgentReader HTML to Markdown Converter is a paid API for AI agents from agent-reader.agent-reader.workers.dev, paid per call via x402, $0.003/call, status unknown (last checked 2026-09-14).

Converts raw HTML strings into clean, LLM-ready markdown by stripping scripts, styles, and boilerplate

## Facts

- Endpoint: POST https://agent-reader.agent-reader.workers.dev/clean
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentreader-html-to-markdown-converter-74d1b4be
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wl2Y2zCoDxesxau03GqRT

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 agentreader-html-to-markdown-converter-74d1b4be -d '<json body>'
```

Example prompt: I already fetched this page's HTML — can you clean it up into markdown by stripping all the scripts, styles, and nav boilerplate so I can feed it to the model?

## When to prefer this

Choose this endpoint when your agent has already fetched the raw HTML of a page and you want to convert it to markdown without making a second network request to retrieve the URL. It is cheaper than the /read endpoint (which fetches and cleans from a URL) and avoids redundant HTTP calls. Ideal for pipelines where HTML is already in hand from a prior crawl, cache, or scrape step.

## Known failure modes

- Malformed or empty HTML string returns an error or empty markdown
- Extremely large HTML payloads may be rejected or truncated
- HTML with unusual encoding may produce garbled markdown
- Pages that are entirely JavaScript-rendered with no static content yield minimal markdown

## How this service works

Convert raw HTML you already have into clean markdown. Send JSON {"html": "..."} and get back markdown with scripts, styles and boilerplate stripped. Cheaper than /read when the agent has already fetched the page.

## Output

Clean markdown text derived from the submitted HTML, with JavaScript, CSS, navigation, ads, and other boilerplate removed — leaving only the human-readable content in a format suitable for LLM ingestion.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "html": {
   "type": "string",
   "description": "Raw HTML string to convert to markdown"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentreader-html-to-markdown-converter-74d1b4be/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-reader.agent-reader.workers.dev](https://www.zero.xyz/host/agent-reader.agent-reader.workers.dev/llms.txt)