API Reference › ChatGPT › Shopping cards

Shopping cards

Product blocks that cloro parses out of a ChatGPT answer — each one carries the title, price, merchant, rating, and per-seller offers behind a recommended item.

Overview

Shopping cards are not a standalone endpoint. They ride along inside the payload returned by the ChatGPT extract call, so there is no separate request to make. When ChatGPT surfaces commercial or product-style content for a prompt, cloro normalizes those cards into a shoppingCards array on the result object.

Extraction is opt-in. Add include.shopping: true to your request body and the cards appear in the response; leave it out and they are skipped. Turning the flag on carries no extra charge. Cards tend to show up when ChatGPT routes the prompt through its lightweight shopping model, and because the model is chosen per request they will not be present in every answer.

Request example

{
  "prompt": "What are the best sneakers under $100?",
  "model": "CHATGPT",
  "country": "US",
  "include": { "shopping": true }
}

Shopping card structure

Every entry in the shoppingCards array holds a set of category tags plus the products grouped under that card.

Field	Type	Description
tags	array	Category labels describing the card, for example `["electronics", "deals"]`.
products	array	The product objects that belong to this card.

Product information

Each product object exposes the commerce details cloro could pull for that item.

Field	Type	Description
title	string	Display name of the product.
position	integer	1-based rank counted flat across every card in the response, not restarted per card.
url	string	Link to the product page, carrying ChatGPT attribution parameters.
description	string	Short product description.
price	string	Current price as shown, for example `"$57.00"`.
featured_tag	string	Style or category label highlighted for the product.
merchants	string	Summary of sellers, for example `"Amazon.in + others"`.
image_urls	array	Product image links.
rating	float	Average rating on a 0–5 scale.
num_reviews	integer	Count of reviews behind the rating.
id	string	Stable identifier for the product.
cite	string	Citation reference token, for example `"turn0product0"`.
offers	array	Per-merchant offers for the product (see below).
offersSeeMoreBoundary	integer	How many offers are visible before a "see more" control.
rating_grouped_citation	object	Rating source attribution with supporting websites.
showcaseMetadata	object	Display metadata used to lay out product imagery.
providers	array	Identifiers of the data providers that fed the product.
productLookupKey	object	Key used to look up refreshed product data.
productLookupData	object	Structured lookup query for the product.
showPriceDisclosure	boolean	Whether a price disclosure should be shown.
analyticsMeta	object	Analytics metadata, including a `productEventUuid`.
metadataSources	array	Origins of the product metadata, for example `["p2"]`.
generatedProductQuery	string	The broader shopping query ChatGPT generated for the item.

Offer information

Each element of offers describes one merchant's listing for the product.

Field	Type	Description
merchant_name	string	Name of the merchant, for example `"Amazon.in"`.
merchant_subtitle	string	Secondary merchant detail.
marketplace_seller	string	Third-party seller operating on the marketplace.
seller_name	string	Seller name.
brand	string	Brand of the product.
product_name	string	Product name as the merchant lists it.
url	string	Offer link with ChatGPT attribution.
price	string	Offer price.
details	string	Stock and delivery notes.
original_price	string	Pre-discount price, when present.
available	boolean	Whether the offer is in stock.
checkoutable	boolean	Whether the offer supports direct checkout.
checkout_payload	string	Encoded data for the checkout flow.
checkout_image_urls	array	Images used during checkout.
is_digital	boolean	Whether the product is a digital good.
price_details	object	Line-item price breakdown (see below).
tag	object	Promotional tag on the offer (see below).
shop_id	string	Identifier of the shop.
provider	string	Provider code, for example `"p2"`.

Price details

When an offer includes a cost breakdown, price_details splits it out.

Field	Type	Description
display_price	string	Formatted price for display.
base	string	Base price of the product.
shipping	string	Shipping cost.
tax	string	Tax amount.
total	string	Total including any added costs.

Offer tag

Field	Type	Description
text	string	Tag label, for example `"Best price"`.
tooltip	string	Explanatory text for the tag.

Rating citation information

Products may carry attribution for where their rating came from via rating_grouped_citation.

Field	Type	Description
title	string	Source title.
url	string	Source URL.
supporting_websites	array	Additional websites backing the rating (see below).
attribution	string	Attribution text; may be null.
pubDate	string	Publication date; may be null.
snippet	string	Excerpt of the source; may be null.
attributionSegments	array	Segmented attribution data; may be null.
refs	array	Reference objects.
hue	string	Color hue hint; may be null.

Supporting website

Entries of rating_grouped_citation.supporting_websites.

Field	Type	Description
title	string	Supporting website title.
url	string	Supporting website URL.
pub_date	string	Publication date; may be null.
snippet	string	Content excerpt; may be null.

Showcase metadata

Layout hints for product imagery, primarily on inline products.

Field	Type	Description
image	object	Image info: `url`, `width`, `height`.
background	object	Background colors: `type`, `primary`, `secondary`.
slots	object	Named display slots with positioning and fit data.

Response example

{
  "success": true,
  "result": {
    "text": "If you're shopping for sneakers under $100, here are a few options...",
    "shoppingCards": [
      {
        "tags": ["stylish casual leather sneaker", "canvas everyday skate-inspired"],
        "products": [
          {
            "title": "Adidas VL Court 3.0",
            "position": 1,
            "url": "https://www.adidas.com/us/vl-court-3.0-shoes/ID8797.html?utm_source=chatgpt.com",
            "price": "$57.00",
            "featured_tag": "stylish casual leather sneaker",
            "merchants": "adidas + others",
            "cite": "turn0product0",
            "image_urls": ["https://images.example-cdn.com/static/AY2CiYu1..."],
            "id": "3250714974047560249",
            "rating": 4.7,
            "num_reviews": 10394,
            "showPriceDisclosure": false,
            "offersSeeMoreBoundary": 3,
            "providers": ["product_info"],
            "metadataSources": ["p2"],
            "offers": [
              {
                "merchant_name": "adidas",
                "seller_name": "adidas",
                "product_name": "Adidas Women's VL Court 3.0",
                "url": "https://www.adidas.com/us/vl-court-3.0-shoes/ID8797.html?utm_source=chatgpt.com",
                "price": "$57.00",
                "details": "In stock online and nearby, delivery Sat - Mon $4.99",
                "original_price": null,
                "available": true,
                "checkoutable": false,
                "is_digital": null,
                "provider": "p2",
                "price_details": { "base": "$57.00", "total": "$57.00" },
                "tag": { "text": "Best price" }
              }
            ]
          }
        ]
      }
    ]
  }
}

Notes

Shopping cards are best treated as opportunistic: their presence depends on how ChatGPT answers a given prompt, and individual fields can be null or absent. Guard for missing keys when you read them. For help interpreting a specific card, reach out at [email protected].