Use casesOperations & logistics
Turn messy warehouse and stock notes into consistent records
Rewrites the free-text notes pickers and stock-takers actually write into consistent records: what happened, which SKU, which location, what next.
- How it works
- Each note — 'box crushed 3pcs w/off', 'loc B12 mixed with B13??', supplier names spelled four ways — is matched against your real SKU list and location scheme with fuzzy lookup, so misspellings and abbreviations still land on the right item. The small model then structures the record: what happened, SKU, location, quantity, action needed. It runs over the backlog in batch, so your stock-adjustment log becomes searchable and countable instead of folklore.
- Data you need
- The notes exported as text from wherever they live — WMS comment fields, a shared spreadsheet, a chat group dump — plus your SKU list and location naming scheme so the model can normalise against something real. Notes must already be digital text; if they only exist on paper they have to be typed up first, as no vision model is served.
- What to expect
- Handles typical shorthand and misspellings well once spot-checked against your team's habits in the first few batches. Genuinely ambiguous notes ('moved the rest') would otherwise produce tidy-looking guesses, so low-confidence rows are marked for a person rather than filled in — and notes relying on tribal knowledge ('put it where Piet always does') stay ambiguous.
- Where people stay involved
- Someone reviews normalised records before any stock adjustment is booked. The model tidies language; it must not change inventory numbers on its own.
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
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 operations & logistics
All 13 →Sort supplier and carrier emails into the right queue
Tags every email to your purchasing or logistics inbox — delay, invoice, complaint — and routes it to the right queue, on your own infrastructure.
Pull order lines out of supplier PDFs and emails into a spreadsheet
Extracts SKU, quantity, price and delivery date from supplier PDFs and emails into rows you can import into your ERP or a spreadsheet.
Check supplier order confirmations against what you actually ordered
Compares each supplier confirmation against your purchase order and flags changed prices, quantities, substituted items and pushed delivery dates.
A morning digest of every delivery problem, in one email
One plain-language email each morning: the day's delayed, failed and held shipments, and the customers and orders behind each tracking number.
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.