First to Market

    The Data Layer for AI Shopping Agents

    AI shopping agents can only be as accurate as the product data they call on. kwery is GTIN-matched, confidence-scored pricing across 12 marketplaces — built to be a single, reliable tool call, not another scraped feed an agent has to second-guess.

    Get API KeyView Documentation· Free tier available · Plans from €399/mo

    Live across marketplaces

    The Gap

    What Merchant Agents Can't See

    Merchant agents can decide. They can't see the market.

    Merchant agents can read a retailer's own sales performance, stock levels, and order history, and draft pricing, promotion, and campaign changes from that data. What they can't see is the market outside the store — what a competitor is charging right now, or whether a listed price is even still current. An agent can draft a confident price change and still be wrong the moment it's compared to reality. kwery is the tool call that closes that gap — three things every price-data result needs, that most feeds don't provide:

    1. Verified identity

      GTIN-matched, not keyword-guessed, so the agent has the actual product, not something similar.

    2. A confidence score per result

      Identity, completeness, price integrity, offer contamination, and freshness, scored individually, so an agent can weigh how much to trust an answer instead of treating every result as equally reliable.

    3. A live, on-demand result

      Fetched at the moment of the call, not read from yesterday's crawl.

    POST · api.kwery.co/job
    {
      "trust": {
        "score": 0.92,
        "detail": {
          "identity": 1.00,
          "completeness": 0.89,
          "price_integrity": 0.95,
          "offer_contamination": 0.97,
          "freshness": 0.75
        }
      }
    }

    Why kwery

    Built for One Request, One Answer

    One synchronous call. A live result, not a cached one.

    Most price-data APIs are built for bulk jobs — submit thousands of SKUs, poll, download later. An agent making a decision mid-conversation can't wait on a queue. kwery's wait parameter holds the request open and returns a single synchronous result in one call — no polling, no job ID to track.

    Every result is fetched at the moment of the request, not read from a cached snapshot with a timestamp attached — the freshness score returned with each result reflects that in real time.

    One call in. One matched product, with its confidence score, back before the agent's next step.

    POST · api.kwery.co/job
    curl -s https://api.kwery.co/job \
      -H "Authorization: Bearer $KWERY_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{"source":"amazon","country":"de","key":"gtin","values":["4006381333962"],"wait":true}'

    Early Use Cases

    Who's Building With This

    Three ways teams are wiring in AI-ready price data.

    Early adopters are using kwery in three ways:

    01

    Retailers building their own shopping assistant

    Feed live competitor and catalog pricing into a customer-facing agent without maintaining a separate data pipeline.

    Feeds → customer-facing agent

    02

    Marketplaces and comparison tools building AI-driven search

    GTIN matching means the agent compares the same product across sources, not similarly-titled listings.

    Feeds → AI search index

    03

    Teams building merchant agents

    A staff-facing agent that drafts pricing and promotion changes needs to know what the market is doing, not just what's in the retailer's own sales data. Ready to wire this in? Read the integration guide →

    Feeds → merchant agent

    No Signup Needed

    Try It Before You Wire It Up

    Prototype first. Go live when you're ready.

    kwery ships a mock server that returns real response shapes with no API key and no credits consumed — prototype a tool definition, test how your agent handles the response, then swap in a live key when you're ready for production.

    POST · docs.kwery.co/_mock
    curl -X POST https://docs.kwery.co/_mock/openapi/job \
      -H "Authorization: Bearer test123" \
      -H "Content-Type: application/json" \
      -H "x-redocly-response-body-example: wait" \
      -d '{"source":"idealo","country":"de","key":"gtin","values":["4006381333962"]}'

    Self-Serve

    One Credit. One Resolved SKU

    Product matching, product page, and offers — billed as a single credit.

    01

    Product Matching

    Identify the correct product within the requested source using GTIN or URL.

    02

    Product Page

    Title, brand, specs, images, and category — fully normalized.

    03

    Offers

    Every seller, price, condition, and shipping option in the offer section.

    Entry Price

    €399 / mo

    Included

    100k credits / mo

    Overage

    €3.99 / 1k credits

    1,000 free credits on signup — no credit card required.

    Support

    Common Questions

    What teams ask before wiring kwery into an agent's tool-calling layer.

    Browse all FAQs

    No — kwery is a REST API your team calls from your own agent's tool-calling layer, giving you control over which results the agent sees and how they're used.

    Yes — see the integration guide for a worked example.

    Yes, via the wait parameter (up to 50 seconds, synchronous).

    Every kwery result is fetched live at request time and carries a confidence score — not a static snapshot with a timestamp attached.

    Give Your Agent Data It Can Trust

    GTIN-matched, confidence-scored pricing across 12 marketplaces — one tool call, one answer.

    Enterprise SLA
    Global Scale