ML Env

Use casesMarketing

Find quotable lines in your reviews for marketing use

Searches your exported customer reviews for verbatim passages that support a theme — 'fast delivery', 'true to size' — as candidate testimonials.

How it works
Your exported reviews are indexed with embeddings. When you ask for a theme — 'fast delivery', 'fits true to size', 'great for beginners' — retrieval finds the verbatim passages that support it, and the model groups and labels them as candidate testimonials for product pages and ads. Retrieval does the finding; the model only organises.
Data you need
An export of your reviews from the shop platform or review service, and clarity on whether the platform's terms and the customer's consent permit marketing reuse. With under a few hundred reviews, doing this by hand is honestly faster.
What to expect
The model paraphrases if you let it, so every quote must be checked word for word against the source. Editing a quote in a way that changes its meaning, or cherry-picking to create a misleading overall impression, is a consumer-law problem, not just bad taste. Platform terms — marketplace reviews especially — often restrict reuse.
Where people stay involved
A person verifies every quote verbatim against the source review, handles consent and the use of names or initials — GDPR applies to reviewer names — and decides where each quote appears.

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.