ML Env

Use casesSelling across languages

First drafts of policy pages in every market's language

Drafts your returns, shipping and terms pages in each market's language — strictly as a working draft for qualified legal review.

How it works
The large model translates your returns policy, shipping information and terms pages into each market's language, keeping legally significant phrasing conservative, and marks passages it considers legally sensitive as a pointer for the reviewer. These pages must exist per language for EU consumer trust and often for compliance, and they change rarely, so a one-off batch job with careful review is the right shape. Nothing is published without that review.
Data you need
Your current policy pages in one language, in their final agreed form. Do not translate a policy that is still being argued about internally.
What to expect
This is the use case where 'sounds right' and 'is right' diverge most. EU consumer-law terms such as Widerrufsrecht or droit de rétractation have fixed legal meanings, and a fluent-sounding near-miss is exactly the failure mode here. The model's own sensitivity flags are a convenience, not a guarantee — do not use them to scope the review. If you cannot budget for human legal review, do not publish machine-translated terms at all.
Where people stay involved
Non-negotiable: a qualified person — a professional legal translator or a lawyer familiar with the target market — reviews the entire text before publishing, not only the passages the model flagged.

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.

European languages

openGPT-X European LLM Leaderboard · FLORES-200 translation, BLEU · 10 models

Previous-generation models — the board has not been rerun on the 2026 roster, so read the order of magnitude, not a ranking of today's models. And BLEU scores adequacy, not tone: it cannot tell you whether the register fits your brand. That is judged on your own copy.

EuroLLM-9B25.6 · EULlama 3.1 70B24.3Mixtral 8x7B17.3Mistral-Nemo 12B17.1Teuken-7B sigma17 · EULlama 3.1 8B17Llama 3 8B15.9Teuken-7B v0.615 · EUCommand-R 35B13.8Mistral-7B v0.313.3
Higher BLEU is closer to a human translationEU-sovereign model

Independent measurement · openGPT-X / Fraunhofer IAIS · captured 2026-07-10

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 selling across languages

All 16 →

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.