# zhuanqian research API – Web Page to Markdown Extractor

> zhuanqian research API – Web Page to Markdown Extractor is a paid API for AI agents from research-api-production-d642.up.railway.app, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-27).

Fetches a public URL and returns its content as clean markdown, along with extracted links, title, and word count

## Facts

- Endpoint: GET https://research-api-production-d642.up.railway.app/paid/extract?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-27
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/zhuanqian-research-api-web-page-to-markdown-extractor-4eb63966
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_XbV6c2apgNIovcyB7p200

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 zhuanqian-research-api-web-page-to-markdown-extractor-4eb63966
```

Example prompt: Can you fetch https://techcrunch.com/2024/01/15/openai-news/ and convert it to markdown so I can read the full article text cleanly?

## When to prefer this

Choose this endpoint when you need to extract readable markdown content from any public URL quickly and cheaply ($0.005 per call). It is ideal for research pipelines, agent workflows that need to read web pages, or any task requiring clean, structured text from arbitrary URLs. The paid /paid/extract route offers higher reliability and limits than the free /v1/* demo route.

## Known failure modes

- Non-public or paywalled URLs may return empty or partial content
- URLs that require JavaScript rendering may not return full page content
- max_chars cap of 50,000 may truncate very long pages
- Invalid or unreachable URLs will result in fetch errors
- Payment failure (insufficient USDC balance or x402 auth issue) blocks the paid route

## How this service works

Research digest (HN/GitHub/arXiv) and web page → markdown extractor. Paid x402 (USDC on Base) routes under /paid/*; free rate-limited demo under /v1/*.

## Output

A JSON object containing the page's markdown-formatted text content, its title, a list of extracted hyperlinks, and a word count. The markdown field holds the main readable content of the page, cleaned of HTML boilerplate.

## 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": "public https URL"
      },
      "max_chars": {
       "type": "integer",
       "default": 20000,
       "maximum": 50000
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com",
  "links": [],
  "title": "Example Domain",
  "markdown": "# Example Domain ...",
  "word_count": 20
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/zhuanqian-research-api-web-page-to-markdown-extractor-4eb63966/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from research-api-production-d642.up.railway.app](https://www.zero.xyz/host/research-api-production-d642.up.railway.app/llms.txt)