# Tollkit Extract – Brief

> Tollkit Extract – Brief is a paid API for AI agents from attest.tollkit.dev, paid per call via x402, $0.007/call, status unknown (last checked 2026-10-11).

Extracts a concise product/page summary (up to 250 words) from any HTTPS URL, billed per-call via x402 micropayment in USDC with no account or API key required.

## Facts

- Endpoint: POST https://attest.tollkit.dev/web/brief?utm_source=zero.xyz
- Price: $0.007/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tollkit-extract-brief-35d4a108
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap__BqKvz8QAuII6l9oAStpx

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 tollkit-extract-brief-35d4a108 -d '<json body>'
```

Example prompt: Can you pull a brief summary of the product page at https://example.com/some-product — keep it under 80 words?

## When to prefer this

Choose this endpoint when you need a lightweight, no-signup, pay-as-you-go page extraction with a controlled output length. It is ideal for agents that process many URLs sporadically (making per-call billing cheaper than subscriptions) and for workflows where the full raw HTML is unnecessary — only a concise brief is needed. Prefer it over full-scrape APIs when cost per call matters and brevity is acceptable.

## Known failure modes

- Non-HTTPS or malformed URL returns a validation error
- Page behind a login wall or bot-detection may return empty or truncated content
- Payment failure or insufficient USDC balance causes a 402 response with payment details
- max_words outside the 10–250 range is rejected with a schema validation error
- Unreachable or slow-loading pages may time out

## How this service works

Pay-per-call product page extraction. No account, no API key: pay in-band with x402 in USDC on Base or Solana.

## Output

A short plain-text summary of the target webpage's content, capped at the requested word count (10–250 words, default 60). The brief distills the page's key information — typically product name, description, and notable details — without markup or boilerplate.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "description": "Absolute https URL of the page."
  },
  "max_words": {
   "type": "integer",
   "default": 60,
   "maximum": 250,
   "minimum": 10
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tollkit-extract-brief-35d4a108/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from attest.tollkit.dev](https://www.zero.xyz/host/attest.tollkit.dev/llms.txt)