Use casesOperations & logistics
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.
- How it works
- The model reads the supplier's confirmation next to your original purchase order and lists the differences: 'line 3: you ordered 200, they confirmed 120; delivery moved from week 32 to week 35'. Instead of a buyer eyeballing two documents, they get a short list of what changed. Confirmation changes that nobody reads closely are exactly what later turns into a stockout or a margin surprise — this makes them visible while there is still time to react.
- Data you need
- Your purchase orders in exportable form (CSV from the ERP or webshop back office) and the supplier confirmations as text-layer PDFs or emails. Without machine-readable POs on your side, this case does not work. Where suppliers use their own article numbers, you need at least a rough code mapping to yours.
- What to expect
- Good at surfacing genuine changes in clean documents. Expect some false alarms on formatting differences — units, pack sizes — until prompts are tuned to your suppliers, and matching fails without a code mapping when article numbers differ. Scanned or photographed confirmations need a separate OCR step first, as no vision model is served.
- Where people stay involved
- The buyer decides what to do with every flagged difference — accept, negotiate, cancel. The system only surfaces discrepancies; it must never auto-accept a changed confirmation.
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.
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.
Draft carrier loss and damage claims with the paperwork attached
Assembles a first draft of a carrier loss or damage claim from your invoice, consignment note and delivery notes, and lists what is still missing.
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.