ML Env

Use casesMarketing

Check draft marketing copy against your own rules before it goes out

Reads draft copy against your written rulebook — banned claims, pricing wording, required disclaimers — and flags likely violations with the rule cited.

How it works
You maintain a plain-language rulebook: claims you must never make, how discounts and 'was/now' prices must be worded, required disclaimers, banned superlatives. Before copy ships, the model reads the draft against the retrieved rulebook and flags likely violations, citing the rule each time. It is a second pair of eyes that never gets bored.
Data you need
The rulebook has to exist in writing. Many small firms have these rules only in the owner's head — writing them down is the real project; the model check is the easy part afterwards.
What to expect
This is a pre-check, not compliance, and it is not legal advice and must never be presented as such. It will miss some violations and raise false positives, so treat every flag as a prompt to look rather than a verdict. Coverage is exactly as good as the written rulebook and no better.
Where people stay involved
Whoever approved copy before still approves it. Anything the model flags as a legal question goes to an actual adviser — this reduces obvious slips, it does not confer compliance.

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.

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.

Also in marketing

All 13 →

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.