ML Env

Use casesCatalogue content

Translate your catalogue into Dutch, German or French

Translates titles, descriptions and attributes for the EU markets you sell to, on hardware in the Netherlands — your content never leaves the EU.

How it works
The large model translates product titles, descriptions and attributes into the languages of the EU markets you sell to, respecting a do-not-translate glossary (brand names, model numbers, protected terms) and your tone guidance. Because it runs on EU-resident hardware, the content never leaves the Netherlands — which matters if your descriptions embed anything commercially sensitive, such as unreleased products.
Data you need
A source-language catalogue export (CSV or shop-platform export). A do-not-translate glossary — most shops do not have one written down, but it can be assembled in an hour from your brand list and SKU naming scheme, and it must be built before the first run. Locale conventions to enforce (decimal commas, size systems — EU 38 is not UK 38). Existing human-translated pages, if you have any, serve as reference style.
What to expect
Output is good machine-translation quality: accurate, but occasionally flat or subtly off-register. That is fine for long-tail SKUs and not a substitute for native copy on the pages that sell your brand. Size and fit conventions are a classic error source — handle unit and size conversions in code, not in the prompt. Skipping the glossary step is the most common failure: without it, brand and model names get 'helpfully' translated.
Where people stay involved
A native speaker reviews at least the top-selling products and all safety and legal text per market. Machine translation of warnings and regulated wording should never ship unreviewed.

Which model, and what it costs to run

Qwen3-32B

This job runs in bulk rather than to a waiting person, so size is not the constraint — we take the strongest independent score on structured output and tool calls that we may serve freely and that fits on a single card.

Licence
Apache-2.0
Weights at 4-bit
18 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
$0.12 / $0.12per M in / out · Nebius AI Studio · EU

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.

Structured output and tool calls

Berkeley Function Calling Leaderboard · v4 · 13 of 18 models measured

Measured in a sandbox, on somebody else's functions. It tells you which models are capable of the shape of the job, not which one will survive contact with your API.

GLM-4.672.38%Kimi K259.06%DeepSeek-V3.254.12%Qwen3-32B48.71%Qwen3-235B-A22B47.99%Qwen3-8B42.57%Qwen3-30B-A3B41.39%Qwen3-14B41.03%
Longer is betterFree to serveConditions apply⚠ answered under 95%

Independent measurement · UC Berkeley (Gorilla project) · board updated 2026-04-12

Writing in your voice

No benchmark measures this

There is no benchmark for this and there is unlikely ever to be one. Anyone who shows you a chart ranking models on marketing copy has drawn it from a model's opinion of another model.

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.

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.