ML Env

Use casesOperations & logistics

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.

How it works
You give it the evidence — order value from the invoice, shipment details from the CMR or label data, the delivery exception notes, and your own description of the damage. The model drafts a structured claim covering the three things carriers require: goods tendered in good condition, condition on arrival, and the amount claimed. It also reminds you which attachments are still missing. Photos are referenced as attachments only — they are not analysed.
Data you need
The commercial invoice, proof of dispatch (CMR note, carrier booking or label), proof of delivery or the driver's damage remark, photos to attach, and a short human-written note on what happened. The models read text only: a handwritten or scanned CMR note must be typed or pasted in, as there is no OCR. The evidence usually exists scattered across email — the value is assembling it into one coherent claim, not digitising paper.
What to expect
Useful drafting help when your evidence is solid; it cannot invent proof, and a well-written claim on thin evidence will still be rejected. It can misstate liability limits (CMR compensation is capped by weight) or confidently miss a carrier- or country-specific formality, so the legal framing needs review. This is drafting help, not legal advice.
Where people stay involved
A person verifies every figure, signs, and files the claim. CMR deadlines are short — reservations at delivery, written claims within days for non-apparent damage — and a human must own the deadline, not the model.

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

Berkeley Function Calling Leaderboard · v4 · 13 of 18 models measured

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.

GLM-4.672.38%Kimi K259.06%DeepSeek-V3.254.12%Qwen3-32B48.71%Qwen3-235B-A22B47.99%Qwen3-8B42.57%Qwen3-30B-A3B41.39%Qwen3-14B41.03%
Longer is betterFree to serveConditions apply⚠ answered under 95%

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.

  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.

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.