# GET /product/ai: $0.01 per call

Product and price from any public product page, even without structured data: uses the page's schema.org/OpenGraph data when present, otherwise AI reads the page text for name, brand, price, currency, availability and SKU. Says which method was used. Respects robots.txt; not charged if it isn't a product page. ?url=...

- **Price:** $0.01 in USDC, the same on Base, Solana, Polygon, Arbitrum. Failed calls are never charged.
- **Free trial:** yes, 20 free calls a day from Claude, Cursor or any MCP client ([set-up](/mcp/setup)).
- **Tier:** deep
- **Answers cached for:** 15 min
- **Data sources:** The product page's structured data; Workers AI (metered, only when there is no structured data)
- **Lane:** Web search and crawling ([OpenAPI](/openapi/web-search.json))
- **Live health:** [status page](/status)

## Free sample

See an answer for the demo input first, free (no payment, 10 a minute): [https://aayatai.com/sample/product-ai](/sample/product-ai). It is a stored real answer when we have one, otherwise an example marked `"kind": "illustrative"`.

```bash
curl "https://aayatai.com/sample/product-ai"
```

## 1. See the price (free)

Call it without paying: you get `402 Payment Required` and a `PAYMENT-REQUIRED` header with the exact price and where to pay.

```bash
curl -i "https://aayatai.com/product/ai?url=https%3A%2F%2Fexample.org%2Fwidget"
```

## 2. Pay and call (TypeScript)

```bash
npm install @x402/fetch @x402/evm viem
```

```ts
import { wrapFetchWithPaymentFromConfig } from "@x402/fetch";
import { ExactEvmScheme } from "@x402/evm";
import { privateKeyToAccount } from "viem/accounts";

// A wallet used only by your agent, holding a little USDC on Base.
const account = privateKeyToAccount(process.env.WALLET_PRIVATE_KEY as `0x${string}`);
const pay = wrapFetchWithPaymentFromConfig(fetch, {
  schemes: [{ network: "eip155:8453", client: new ExactEvmScheme(account) }],
});

const res = await pay("https://aayatai.com/product/ai?url=https%3A%2F%2Fexample.org%2Fwidget");
console.log(await res.json());
```

## 3. Or as an MCP tool

```ts
// MCP server: https://aayatai.com/mcp (Streamable HTTP). With the x402 MCP client (see /start):
const result = await client.callTool("product-ai", {"url":"https://example.org/widget"});
```

## Inputs

- `url` **(required)** (string): A product page address.

Bad inputs are rejected with HTTP 400 before any payment is asked for.

## Example answer

```json
{
  "url": "https://example.org/widget",
  "found": true,
  "product": {
    "name": "Example Widget",
    "brand": "Example",
    "description": "A very good widget.",
    "sku": "W-1",
    "gtin": "5012345678900",
    "mpn": null,
    "price": 19.99,
    "lowPrice": null,
    "highPrice": null,
    "currency": "GBP",
    "availability": "InStock",
    "condition": "NewCondition",
    "seller": "Example Shop",
    "priceValidUntil": null,
    "rating": 4.6,
    "reviewCount": 128,
    "image": "https://example.org/widget.jpg",
    "url": "https://example.org/widget",
    "source": "json-ld"
  },
  "products": [
    {
      "name": "Example Widget",
      "brand": "Example",
      "description": "A very good widget.",
      "sku": "W-1",
      "gtin": "5012345678900",
      "mpn": null,
      "price": 19.99,
      "lowPrice": null,
      "highPrice": null,
      "currency": "GBP",
      "availability": "InStock",
      "condition": "NewCondition",
      "seller": "Example Shop",
      "priceValidUntil": null,
      "rating": 4.6,
      "reviewCount": 128,
      "image": "https://example.org/widget.jpg",
      "url": "https://example.org/widget",
      "source": "json-ld"
    }
  ],
  "method": "structured",
  "fetchedAt": "2026-09-28T12:00:00.000Z"
}
```

## Related

- [GET /search/open](/services/search-open) ($0.002): Cheapest search: Wikipedia articles, Hacker News stories, DuckDuckGo instant answers and Stack Overflow questions in one call, merged, de-duplicated and ranked,
- [GET /search](/services/search) ($0.003): Live search, open-sources tier: fresh results from Wikipedia, Hacker News, DuckDuckGo instant answers and Stack Overflow, merged, de-duplicated and ranked (titl
- [GET /search/answer](/services/search-answer) ($0.03): Search, read and summarise in one call (open-sources tier): finds pages via Wikipedia, Hacker News, DuckDuckGo and Stack Overflow, reads the top ones (robots.tx
- [GET /metadata](/services/metadata) ($0.002): A web page's metadata in one cheap call: title, description, canonical URL, language, site name, preview image, OpenGraph and Twitter card tags, author and date
- [GET /feed](/services/feed) ($0.003): Latest posts from any site or feed as clean JSON: pass a feed URL or just the site's address and we find its RSS, Atom or JSON Feed (from the page's links or co
- [POST /page/changes](/services/page-changes) ($0.002): Watch any public page for changes: we fetch it now (robots.txt respected), fingerprint its text and return a token.
- [POST /page/changes/summary](/services/page-changes-summary) ($0.008): Page change detection with an AI summary: like /page/changes (send back the token from your last check), plus a two-sentence summary of what changed and whether
- [GET /product](/services/product) ($0.003): Product and price from any public product page, as clean JSON: name, brand, price, currency, availability, condition, SKU/GTIN, seller, rating and image, read f

New here? [Getting started in 60 seconds](/start). All services: [Aayat AI](/).