Use casesOperations & logistics
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.
- How it works
- The large model reads order confirmations, dispatch notes and quotes that arrive as PDF attachments or pasted email text, and pulls each line item into structured rows: SKU, description, quantity, unit price, delivery date. Because it reads the document rather than a fixed template, it copes with every supplier laying things out differently — exactly where rule-based parsers break. Extracted lines are validated automatically (do the lines sum to the stated total?) before anyone sees them.
- Data you need
- The PDFs or emails with a real text layer — documents generated by the supplier's system, not photos or scans. A mapping of supplier product codes to your SKUs makes the output far more useful; most SMBs have this partially in their ERP already. Scanned or photographed documents need a separate OCR step first, as no vision model is served, and poor scans limit everything downstream.
- What to expect
- It removes the typing, not the checking. Clean digital documents extract well; occasional shifted or hallucinated values are a known failure mode of LLM extraction, which is why the automatic total checks and human review stay in the pipeline.
- Where people stay involved
- A person reviews every extracted row before it enters the ERP, at least for the first months. A wrong quantity or price that flows into purchasing unreviewed is expensive.
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.
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.
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.