# Tollkit Extract Batch

> Tollkit Extract Batch is a paid API for AI agents from extract.tollkit.dev, paid per call via x402, $0.15/call, status unknown (last checked 2026-10-02).

Extracts structured product data (name, brand, SKU, price, availability) from up to 5 product page URLs in a single paid call.

## Facts

- Endpoint: POST https://extract.tollkit.dev/extract/batch?utm_source=zero.xyz
- Price: $0.15/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tollkit-extract-batch-c4d41ab6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_5DLxBAP1xhtt2vsUlREL4

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-batch-c4d41ab6 -d '<json body>'
```

Example prompt: Can you pull the product details — name, price, availability, and SKU — from these five URLs at once: https://store-a.com/product/123, https://store-b.com/item/456, https://store-c.com/p/789, https://store-d.com/goods/321, https://store-e.com/buy/654? I want to compare them side by side without paying separately for each one.

## When to prefer this

Choose this endpoint when you need to extract and compare product data from 2–5 URLs in a single atomic call and payment, rather than calling a single-URL extractor multiple times. Ideal for price comparison, competitive intelligence, or multi-store availability checks where you want one charge and one round-trip. Prefer the single /extract endpoint if you only have one URL.

## Known failure modes

- One or more URLs unreachable or returning non-200 responses — those items are returned with error status but successful ones are still billed
- All URLs fail — call is not charged
- URL points to a non-product page (category, homepage) — extraction returns empty or partial data
- Redirect encountered when allow_redirect is false — URL fails extraction
- Duplicate URLs submitted — deduplicated automatically, not double-billed
- Rate limiting or bot protection on target site — extraction may fail for that URL

## How this service works

Compare product prices across up to 5 stores in one call: give up to 5 product page URLs, get each one's price, currency, stock, name, brand and images as schema.org/Product JSON. One payment for the whole set. Use for price comparison, deal finding and checking a shortlist. $0.15 flat; if every URL fails you are not charged.

## Output

Returns an array of schema.org/Product-compatible JSON objects for each URL, each containing product name, brand, SKU, price, currency, and availability. URLs that fail to extract are returned with an error status but the call is still charged for successfully extracted URLs; if every URL fails, the call is not charged.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "urls": {
   "type": "array",
   "items": {
    "type": "string",
    "format": "uri"
   },
   "maxItems": 5,
   "description": "Up to 5 absolute https:// product page URLs. Duplicates are removed and not billed twice."
  },
  "allow_redirect": {
   "type": "boolean",
   "default": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tollkit-extract-batch-c4d41ab6/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from extract.tollkit.dev](https://www.zero.xyz/host/extract.tollkit.dev/llms.txt)