# Notte Scrape From HTML

> Notte Scrape From HTML is a paid API for AI agents from Notte at mpp.orthogonal.com, paid per call via MPP, $0.021/call, status unknown (last checked 2026-10-09).

Extracts structured content from raw HTML string input without launching or managing a browser session

## Facts

- Endpoint: POST https://mpp.orthogonal.com/notte/scrape_from_html?utm_source=zero.xyz
- Price: $0.021/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-09
- Activations on Zero: 0
- Provider: Notte
- Docs: https://api.notte.cc
- Website: https://api.notte.cc
- Tags: browser, automation, agents, web, compute
- Canonical page: https://www.zero.xyz/c/notte-scrape-from-html-f0bc3c58
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_GoTr7kgJOntiuMToKYo0s

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 notte-scrape-from-html-f0bc3c58 -d '<json body>'
```

Example prompt: I already have the raw HTML from this product listing page — can you extract the product name, price, description, and any available specs from it without spinning up a browser?

## When to prefer this

Use this endpoint when you already have the raw HTML source (e.g. fetched via your own HTTP client) and need structured data extracted from it without incurring the overhead or cost of launching a full browser session. It is faster and cheaper than browser-based scraping and ideal for static HTML content where JavaScript execution is not required.

## Known failure modes

- Malformed or incomplete HTML may result in partial or empty extraction
- HTML with heavy JavaScript rendering may be missing dynamic content since no browser executes scripts
- Missing or unclear extraction instructions may yield generic rather than targeted output
- Very large HTML payloads may hit request size limits
- Rate limits exceeded returning 429 errors

## How this service works

Extract structured content from raw HTML without using a browser

## Output

Returns structured content extracted from the provided HTML, with relevant fields parsed out such as text, links, headings, and any user-specified data points — all without requiring a live browser session.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/notte-scrape-from-html-f0bc3c58/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mpp.orthogonal.com](https://www.zero.xyz/host/mpp.orthogonal.com/llms.txt)