Check every listing carries the safety and manufacturer details EU rules now require
Audits every listing's text against a GPSR checklist your compliance owner writes, flagging missing manufacturer details, addresses and warnings per SKU.
- How it works
- Since 13 December 2024, GPSR requires EU-facing listings to show the manufacturer's name, postal and electronic address, an EU responsible person where the manufacturer is outside the EU, a product identifier, and applicable warnings — visible before purchase, and marketplaces do delist for gaps. The model audits each listing's text fields against a checklist your compliance owner writes, and flags what is missing or malformed per SKU. It is a reading-at-scale job: tedious for people, mechanical for a model.
- Data you need
- Listing exports with the text fields where this information lives (title, description, attribute fields), and a written checklist per product category — what counts as a warning, which categories need age labels — prepared by whoever owns compliance, possibly with legal advice. Master data on manufacturers and EU responsible persons must already exist somewhere: the model cannot invent an EU responsible person, and in many smaller shops this master data has never been collected. Building it is a separate, manual project.
- What to expect
- A model pass reduces obvious gaps across thousands of listings; it does not certify compliance, and category-specific obligations for toys, cosmetics or electronics go beyond what a generic checklist catches. It is text-only: anything shown only in product images — warning symbols, labels photographed on packaging — is invisible to the audit, so listings can be flagged for information that exists in an image, or pass on text while the buyer-visible detail is image-only. If the required manufacturer data simply does not exist in your systems, this surfaces the problem but cannot solve it. This is not legal advice.
- Where people stay involved
- The checklist itself is a legal and compliance decision made by a human; the model only executes it. Flagged listings go to a person who sources the missing data. Borderline calls — whether a phrase counts as a valid warning, whether an address format is acceptable — should be treated as 'needs review', not as a model verdict.
Which model, and what it costs to run
Qwen3-32B
This job runs in bulk rather than to a waiting person, so size is not the constraint — we take the strongest independent score on structured output and tool calls that we may serve freely and that fits on a single card.
- Licence
- Apache-2.0
- Weights at 4-bit
- 18 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
- $0.12 / $0.12per M in / out · Nebius AI Studio · EU
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.
Structured output and tool calls
Measured in a sandbox, on somebody else's functions. It tells you which models are capable of the shape of the job, not which one will survive contact with your API.
Independent measurement · UC Berkeley (Gorilla project) · board updated 2026-04-12
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.
- 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.
- 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.
- 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 catalogue content
All 14 →Turn supplier spec sheets into first-draft product descriptions
Drafts product descriptions overnight from the supplier data you already hold, in your shop's voice — a review job instead of a from-scratch writing job.
Pull sizes, materials, colours and other attributes out of messy supplier text
Reads free-text supplier info and fills a fixed field list — material, dimensions, colour, EAN — returning structured rows for your PIM or shop admin.
Sort new products into the right category in your shop
Embeddings shortlist the most plausible categories for each new product; a small model picks one and explains why — workable even on large category trees.
Write page titles and meta descriptions for every product and category page
Drafts an SEO title and meta description for every page from real product attributes, within your character limits — economical even at long-tail scale.
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.