# ViewportWitness HTML to Markdown Extractor

> ViewportWitness HTML to Markdown Extractor is a paid API for AI agents from qa.honeygate.app, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-13).

Fetches a public URL and deterministically converts its HTML content into clean, readable Markdown text

## Facts

- Endpoint: POST https://qa.honeygate.app/v1/extract?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/viewportwitness-html-to-markdown-extractor-720f77bb
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_0w87e-OnvvDY5xHftKbfW

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 viewportwitness-html-to-markdown-extractor-720f77bb -d '<json body>'
```

Example prompt: Can you fetch https://techcrunch.com/2024/05/01/some-article and extract it as clean markdown — keep the output under about 3000 tokens worth of content?

## When to prefer this

Choose this endpoint when you need a deterministic, clean, reproducible Markdown extraction from a public URL — particularly when you want predictable token-bounded output suitable for LLM context windows. It is well-suited for agent pipelines that need to ingest webpage content without rendering JavaScript. Prefer alternatives if the page is heavily JavaScript-rendered or if you need screenshot/visual rendering rather than text.

## Known failure modes

- URL is not publicly accessible or returns a non-200 status — extraction fails with an error
- URL points to a non-HTML resource (PDF, image, binary) — may return empty or garbled markdown
- maxOutputTokens set below 500 or above 12000 — rejected by schema validation
- Page content is JavaScript-rendered only — static HTML extraction may return minimal content
- Network timeout fetching the target URL — returns a fetch error

## How this service works

DOM to Markdown: extract readable content from a public HTML webpage

## Output

Returns clean Markdown-formatted text extracted from the target webpage's HTML, with an optional token budget controlling how much content is returned. The output strips away navigation, ads, and markup to deliver the meaningful readable content of the page.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "example": "https://example.com",
   "description": "Public HTTPS URL to check"
  },
  "maxOutputTokens": {
   "type": "integer",
   "maximum": 12000,
   "minimum": 500,
   "description": "Optional approximate Markdown output budget."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/viewportwitness-html-to-markdown-extractor-720f77bb/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from qa.honeygate.app](https://www.zero.xyz/host/qa.honeygate.app/llms.txt)