Product Lookup API: Your Product in AI Shopping Answers
Look up one product in ChatGPT, Google AI Overviews, AI Mode, Copilot and Naver AI Tab: which engines show it, at which merchants and prices, the pages each answer cites, and how it compares with your competitors.
CopilotWhich engines show your product
Send a product name and a country, US or KR. For each engine, found tells you whether its answer showed the product, and otherListings holds the other products it showed. summary.foundIn and summary.notFoundIn sort the engines into two lists.
Merchants, prices and reviews
Each listing an answer shows names its merchant, price and source catalog, with stock, rating, review count and catalog ids wherever the engine supplies them. On ChatGPT, modelSees holds what its answering model was given about the product, and chatgpt_widget listings carry the shops and prices ChatGPT wrote in its widget cards.
The pages behind each answer
citedPages lists the pages each answer cites. summary.citedDomains groups them by site with the engines that cited each one, and summary.merchants lists every merchant with the engines that showed it and its price range.
Your product next to your competitors
Add up to five competitor products. Each one gets the same asks as yours, and comparison[] lines them all up engine by engine.
- found: which engines showed each product.
- listings and merchants: how many listings each product got, from how many merchants.
- mostReviewed and priceRange: the listing with the most reviews, and the price range each engine showed.
- prompts: how many shopper prompts each engine answered, and how many of those answers showed or named the product.
What shoppers ask
Add up to three shopper prompts, such as "best eye cream for puffiness". Every engine answers each prompt as written, and prompts[] reports which of your products the answer showed as listings (shown) and which its text names (named).
Engines and asks per market
Each market asks the engines that show product listings there. List engines to choose your own.
- US: ChatGPT gets "Buy {product}" and "Find the best price for {product}", and Google AI Overviews, AI Mode and Copilot get the product name.
- KR: Naver AI Tab and AI Mode get the product name, and ChatGPT gets "{product} 구매" and "{product} 최저가".
- Gemini joins when engines lists it. In KR, so do Google AI Overviews and Copilot.
Submit to POST /v1/product-lookup
Send your product with up to five competitors and three shopper prompts. This lookup asks four engines about three products and two prompts: 23 asks for 40 credits. idempotencyKey becomes the lookup id.
curl -X POST https://api.querying.ai/v1/product-lookup \
-H "Authorization: Bearer $QUERYING_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"product": "belif Moisturizing Eye Bomb",
"country": "US",
"competitors": [
"Clinique All About Eyes",
"CeraVe Eye Repair Cream"
],
"prompts": [
"best eye cream for puffiness",
"best moisturizing eye cream"
],
"idempotencyKey": "eye-bomb-us"
}'Every ask is a task
The response lists each ask with its task, and credits.creditsToCharge adds up their price. Asks run, bill and send webhooks like any other task. Sending the same id again returns the existing asks and adds only the missing ones.
{
"success": true,
"lookup": {
"id": "eye-bomb-us",
"product": "belif Moisturizing Eye Bomb",
"competitors": [
"Clinique All About Eyes",
"CeraVe Eye Repair Cream"
],
"prompts": [
"best eye cream for puffiness",
"best moisturizing eye cream"
],
"country": "US",
"engines": [
"CHATGPT",
"GOOGLE",
"AIMODE",
"BING_COPILOT"
]
},
"summary": {
"total": 23,
"succeeded": 23,
"failed": 0
},
"credits": {
"creditsToCharge": 40,
"creditsCharged": 0
},
"asks": [
{
"engine": "CHATGPT",
"taskType": "CHATGPT",
"role": "product",
"prompt": "Buy belif Moisturizing Eye Bomb",
"success": true,
"task": {
"id": "56be57f3-…",
"taskType": "CHATGPT",
"status": "QUEUED",
"priority": 1,
"createdAt": "2026-10-20T09:22:43.422Z",
"idempotencyKey": "eye-bomb-us:CHATGPT:buy"
}
},
"…"
]
}Read it with GET /v1/product-lookup/:id
Poll the lookup id until lookup.status is COMPLETED, or read it whenever an ask's webhook arrives. Read and store the result within 24 hours of its asks completing.
curl https://api.querying.ai/v1/product-lookup/eye-bomb-us \
-H "Authorization: Bearer $QUERYING_API_KEY"Cost
A product costs 10 credits and a shopper prompt 5, whichever engines you ask. Your product and each competitor count as products, so the lookup above costs 40 credits. Each product's price is split across its asks, a failed ask returns its credits to your balance, and a resend charges only the asks it adds.
View pricing →| Plan | 1,000 products |
|---|---|
| Basic | ≈ $25.00 |
| Max | ≈ $10.00 |
Effective rates assume all included monthly credits are used.
Measured on 50 products
On 2026-10-20 we looked up 50 products through the production API, 25 in the US and 25 in Korea.
- US: Copilot showed all 25 products, Google AI Overviews and AI Mode 23 of 25.
- KR: Naver AI Tab showed all 25 products, AI Mode 13 of 25.
- ChatGPT, with both asks and its widget cards, showed the product in all 24 US runs and all 20 Korean runs.
- Across repeated runs a merchant listing kept its price, rating and review count in 307 of 316 values. Which listings appear changes from run to run, so read trends across several lookups.
Built for these teams
querying.ai gives every team that needs to understand AI search a single, structured data source.
GEO & AEO Monitoring
Track how AI search surfaces mention your brand, products, and competitors across engines, countries, and prompts.
Learn more
Competitive Intelligence
See what AI engines recommend in your market in real time: which brands get cited, which products surface.
Learn more
Agency Dashboards
Monitor dozens of clients across engines and regions simultaneously with batch APIs and webhooks.
Learn moreResearch & Analysis
Study AI search behavior across markets with structured data for academic research, content strategy, and SEO.
Learn moreExplore related capabilities
Start with 500 free credits
Run your first task in the Playground, or call the API with your key.