ML Env

Use casesMarketing

Turn blog posts and product pages into a week of social drafts

Repurposes blog posts and product pages into per-channel social drafts — LinkedIn, Instagram, X — as a weekly queue for a human to review and schedule.

How it works
It takes text content you already have — a blog post, a new product page, a customer story — and redrafts it per channel: a LinkedIn post, an Instagram caption, a short X or Threads version, each following your format rules for that channel. It runs as a weekly batch producing a queue for a human to review, pair with images and schedule. Text only: it drafts the words, not the visuals.
Data you need
The source content itself, plus a one-page note per channel: length, tone, hashtag conventions, emoji policy, what you never post. A few examples of past posts you liked help the drafts sound like you.
What to expect
This works as a repurposing machine, not a social media manager. Drafts get samey without editing — the model recycles the same hooks, and this is where the small model is weakest; brands fussy about voice may get better drafts from the larger model at higher cost. No vision model is served, so captions are written without seeing the image, and the model has no sense of current trends or shifts in platform culture.
Where people stay involved
A person edits, chooses the accompanying image, checks the words actually match the visual, and schedules everything. Reactive and topical posting — trends, news, memes — should not be delegated at all; the model has no idea what is happening this week.

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.