# Tollkit Extract

> Tollkit Extract is a paid API for AI agents from chain.tollkit.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-14).

Extracts structured product data from a single product page URL, paid per-call in USDC via x402 with no account or API key required.

## Facts

- Endpoint: POST https://chain.tollkit.dev/extract?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tollkit-extract-1a0c5bff
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_oMjHlQ7jCf-7a8n0aR0dq

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-1a0c5bff -d '<json body>'
```

Example prompt: Can you extract the product details from this page: https://www.example.com/products/wireless-headphones-xb500? I want the name, price, description, and any specs listed.

## When to prefer this

Choose Tollkit Extract when you need to scrape a single product page on a pay-per-use basis without signing up for an account or obtaining an API key. It is ideal for ad-hoc product data extraction, price lookups, or catalog enrichment tasks where you want to pay only for what you use via x402 in USDC on Base or Solana. Prefer this over headless browser solutions or full crawlers when you need structured product output quickly and cheaply from one URL at a time.

## Known failure modes

- URL redirects to a non-product page and allow_redirect is false — call refused at no charge
- URL is a search or category page rather than a single product page — extraction rejected
- URL is login-gated or requires authentication — cannot extract
- URL is not a valid https:// URI — validation error
- URL points to a private or local address — rejected
- Page content is not recognized as a product listing — extraction may return empty or partial data
- Payment in USDC fails or is insufficient — request rejected with 402

## 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

Structured product data extracted from the target page, including fields such as product name, price, description, images, and specifications. If the URL redirects to a different page (e.g. a category listing) and allow_redirect is false, the call is refused without charge.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "description": "Absolute https:// URL of ONE product page. Not a search or category page, not a login-gated page, and not a private address."
  },
  "allow_redirect": {
   "type": "boolean",
   "default": false,
   "description": "By default a URL that redirects to what looks like a different page (a discontinued item bouncing to its category listing) is refused free of charge rather than answered with the wrong product."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tollkit-extract-1a0c5bff/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from chain.tollkit.dev](https://www.zero.xyz/host/chain.tollkit.dev/llms.txt)