# ResearchPi Web Page Reader

> ResearchPi Web Page Reader is a paid API for AI agents from agent-research-api.onrender.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-28).

Fetches and extracts readable plain text, title, and links from a single public HTTPS HTML page, returning the source URL and retrieval timestamp.

## Facts

- Endpoint: POST https://agent-research-api.onrender.com/v1/read?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-28
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/researchpi-web-page-reader-a1760acd
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_WGd4JwZaxW38AjOxFyaJD

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 researchpi-web-page-reader-a1760acd -d '<json body>'
```

Example prompt: Can you fetch and pull out all the readable text, title, and links from this page: https://www.example.com/article/ai-trends-2025?

## When to prefer this

Choose this endpoint when you need fast, lightweight extraction of readable text, title, and links from a known public HTTPS HTML page. It is ideal for reading articles, documentation, or landing pages without needing a full browser or JavaScript execution. Prefer it over headless-browser solutions when the target page is static HTML. Not suitable for JavaScript-heavy SPAs, PDFs, login-required pages, or bulk crawling of entire websites.

## Known failure modes

- Non-HTTPS or private/intranet URLs are rejected
- Pages requiring JavaScript rendering return incomplete or empty text
- Login-gated or paywalled pages are inaccessible
- PDF or non-HTML content types are not supported
- Pages exceeding 2 MB HTML or 60,000 text characters are truncated or rejected
- Slow or unreliable target servers may cause timeouts
- Malformed or invalid URLs return an error

## How this service works

ResearchPi: Extract readable text, title and links from one public HTTPS HTML page. Source URL and retrieval time included. No JavaScript, PDF, login or private network access. Maximum 2 MB HTML / 60,000 text characters.

## Output

Returns the extracted plain text body (up to 60,000 characters), the page title, a list of hyperlinks found on the page, the original source URL, and the retrieval timestamp. No JavaScript-rendered content, PDFs, login-gated pages, or private network resources are supported. HTML input is capped at 2 MB.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "maxLength": 2048
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/researchpi-web-page-reader-a1760acd/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-research-api.onrender.com](https://www.zero.xyz/host/agent-research-api.onrender.com/llms.txt)