Find out what shoppers search for that you don't stock
Clusters your search logs by meaning and flags what shoppers keep looking for that you don't sell — a demand-gap report from a log nobody reads.
- How it works
- Your raw search-log queries are clustered by meaning using embeddings, then the small language model names each cluster in plain language and flags clusters with high volume but poor results — 'people keep searching for phone stands; you sell none', or 'strong demand for size 46, mostly out of stock'. The output is a periodic demand-gap report from a log nobody currently reads.
- Data you need
- On-site search logs with query text and result counts, ideally a few months' worth. Many SMB shops never enabled search logging — if so, enable it and come back in about eight weeks; there is no shortcut.
- What to expect
- Good at surfacing patterns spread across thousands of differently worded queries that no one would spot by skimming. But small shops have small logs: below a few thousand queries a month, clusters get noisy and a human skimming the raw log may do just as well. Bot and internal-staff queries need filtering or they dominate the clusters.
- Where people stay involved
- A buyer or owner interprets the report and decides what to stock — the model finds patterns, it knows nothing about your margins, suppliers or seasonality.
Which model, and what it costs to run
Qwen3-8B
No public benchmark ranks this particular job, so this is not a leaderboard pick — it is where we would start: small, permissively licensed, and strong wherever it has been measured. We prove it on your own content before anything ships.
- Licence
- Apache-2.0
- Weights at 4-bit
- 5 GB
- Context
- 32K tokens
- Publisher
- Alibaba (Qwen Team)
What the hardware costs
One 48 GB card holds it
- Rent in the EU
- $1.60/hrScaleway, Paris (PAR2)
- Buy the card
- $7,569new, one-off
- Or rent it by the token
- $0.04 / $0.04per M in / out · DeepInfra
Hardware only, third-party prices from 2026-07. The figure excludes the KV cache, which grows with context length and how many people use it at once — sized properly in a conversation, not guessed here. Renting by the token is cheaper up front; why our customers still self-host is below.
Search over your own catalogue
No benchmark measures this
MTEB and BEIR rank embedding models, but their evaluation sets sit inside the models' training data. Scores fall by double-digit nDCG on a private corpus, so the ranking does not transfer to your catalogue.
So we do not show a chart here. We measure it on your own content, in the first week, and you see the result before anything ships.
The API is cheaper per token. Here is why our customers don't use it.
We will not pretend otherwise: renting a model by the token from a serverless API costs less per million tokens than a card we run for you. We show that price on every use-case page. What it does not include is the part a shop with a customer database actually pays for.
- 01
Your data never leaves hardware you can point at
A serverless "we don't retain your data" is a clause in a contract. Running the model on a card in Amsterdam is a fact of architecture: your catalogue, tickets and customer records are never sent to a third party at all. For a GDPR audit, that is the difference between a promise and a floor plan.
- 02
The price cannot move without your say-so
A serverless rate card is somebody else's lever. The provider can raise the price, retire the model, or change the terms, and your cost moves with it. The same model on the same card costs the same next year — you own the number.
- 03
The model cannot be taken away
Hosted APIs deprecate models on their own schedule; the one you built on can be gone in a quarter. An open-weight model on your own hardware runs for as long as you keep the lights on. No vendor can end-of-life it out from under you.
And the price gap closes with volume: past a card you keep busy — very roughly four billion tokens a month — owning is cheaper outright, even before the three reasons above.
Getting a case like this one from a conversation to production takes about two months, and you can stop at the end of any phase.
Also in search & discovery
All 12 →Let shoppers search in their own words, not your catalogue's words
Meaning-based search next to your keyword search, so loosely phrased queries find the right products even when no words match your titles.
Stop losing sales on 'no results found' pages
When keyword search returns nothing, the query falls through to embedding search and shows the closest products instead of a dead end.
Handle misspellings, synonyms and mixed-language queries without maintaining dictionaries
Multilingual embeddings put 'trui', 'pullover' and 'jumper' near each other, cutting the need for hand-maintained synonym lists in an EU shop.
Let customers describe the look and find matching products
Shoppers describe a style in plain words — 'minimalist Scandinavian living room, oak and off-white' — and get products whose text matches it.
Next
Tell us what your team does by hand
Describe the process that takes the most time. We will say plainly whether a model is the right tool for it.