# NovaPath Web Page Reader

> NovaPath Web Page Reader is a paid API for AI agents from instructional-decision-engine-x402.vercel.app, paid per call via x402, $0.002/call, status unknown (last checked 2026-11-01).

Fetches and returns clean bounded text from up to two permitted public HTTPS pages or text-layer PDFs in a single paid request, including URLs, retrieval times, and content hashes.

## Facts

- Endpoint: POST https://instructional-decision-engine-x402.vercel.app/agent/read?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-01
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/novapath-web-page-reader-85c3d8bb
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_liaqkA8zWh4Q4RRip1i45

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 novapath-web-page-reader-85c3d8bb -d '<json body>'
```

Example prompt: Can you read the content of https://example.com/report.pdf and https://example.com/summary for me and return the clean text from both, along with when they were retrieved?

## When to prefer this

Choose this endpoint when you need clean, bounded text from one or two specific public HTTPS pages or text-layer PDFs without needing a full browser, OCR, or authentication. It is ideal when you want verifiable metadata (content hash, retrieval time) alongside the text, and when you can confirm the URLs are publicly accessible and permitted. Prefer alternatives if you need JavaScript rendering, login access, OCR on scanned documents, or more than two URLs per request.

## Known failure modes

- Any single failed URL read prevents settlement and returns an error
- URLs blocked by robots.txt or access restrictions are rejected
- Login-required pages cannot be read and will fail
- JavaScript-rendered content is not supported (no browser rendering)
- Scanned PDFs without a text layer fail since OCR is not supported
- URLs with query strings or fragments are rejected by the pattern constraint
- More than two URLs in a single request is rejected
- Non-HTTPS URLs are rejected

## How this service works

Read one or two permitted public HTTPS pages or text-layer PDFs in one paid request. Return clean bounded text, original URLs, retrieval times, content hashes and reading limits. No model call or provider key required from the buyer. Respect robots and access restrictions; any failed requested read prevents settlement. No browser rendering, OCR or login.

## Output

Returns clean bounded text extracted from the requested URL(s), the original URL(s), retrieval timestamps, content hashes, and reading limits. If any requested URL fails to load, the entire request fails and no settlement occurs.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "urls": {
   "type": "array",
   "items": {
    "type": "string",
    "pattern": "^https://[^?#]+$",
    "maxLength": 1000,
    "minLength": 1
   },
   "maxItems": 2,
   "minItems": 1
  },
  "permissionConfirmed": {
   "type": "boolean",
   "const": true
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/novapath-web-page-reader-85c3d8bb/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from instructional-decision-engine-x402.vercel.app](https://www.zero.xyz/host/instructional-decision-engine-x402.vercel.app/llms.txt)