ML Env

Use casesSearch & discovery

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.

How it works
A shopper types 'minimalist Scandinavian living room, oak and off-white' or 'outfit for a summer wedding, not too formal'. The small language model decomposes the description into concrete attributes — colour, material, style, occasion — then retrieval finds products matching each, assembled into a 'complete the look' set.
Data you need
Product descriptions that actually contain style, colour, material and occasion information. This is the weak point: many SMB catalogues don't have it. If yours doesn't, the attribute-extraction case in this group is the prerequisite, not this one.
What to expect
Works best in fashion and home categories with rich descriptions; mediocre elsewhere. It is text only — no vision model is currently served, so 'upload a photo of your room and match it' is not on offer, and that is the version customers imagine, so be upfront about it. The model has no taste, only text similarity: pairings that clash stylistically but read similarly on paper will occur.
Where people stay involved
A merchandiser curates which categories participate and reviews example 'looks' before and after launch, because stylistic judgement stays with a person.

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.

  1. 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.

  2. 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.

  3. 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 →

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.