ML Env

Use casesMarketing

Turn a bullet list into this week's newsletter

You supply the offers, dates and prices as rough bullets; the model drafts the full newsletter in your established voice, with subject line options.

How it works
You write this week's substance as rough bullets — offers, products, dates, one story. Retrieval pulls your past issues as a style reference, and the large model drafts the full newsletter in your established voice. What comes back is a structured draft with subject line options, not a finished send.
Data you need
6-12 past newsletters for voice, and this week's actual content as bullets: exact prices, dates and product links. The model cannot know your promotions; it can only phrase them.
What to expect
The bullets are the value — a lazy brief produces a hollow newsletter. The model will happily write around a missing price by guessing, so every number must come from you. It also has no view on deliverability or on what your list responds to; those judgements stay with whoever presses send.
Where people stay involved
An editor does the final pass every time, verifying prices, dates and links and deciding what leads. Subject line choice and send timing stay human.

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.