ML Env

Use casesOperations & logistics

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.

How it works
The small model reads each incoming email and assigns one of your categories: order confirmation, price change, delivery delay, invoice, complaint, spam. The tag routes the email to the right folder or person, so whoever handles delays sees delays first instead of scrolling past newsletters. Classification takes a second or two and the email text never leaves the server.
Data you need
A shared mailbox reachable by IMAP or a forwarding rule, and a list of the 5–15 categories you actually use. A few dozen example emails per category let you check the tags are right before trusting them.
What to expect
Routine, single-topic emails are tagged reliably once the categories are settled. Mixed-topic emails ('here's the invoice, also your pallet is delayed') get misfiled sometimes, and heavily overlapping categories drag accuracy down — merge them if they do. It only routes; it does not act on anything.
Where people stay involved
Nobody approves individual tags, but someone should spot-check the queues weekly and triage an 'unsure' bucket. Anything tagged as a complaint or legal matter still needs prompt human reading regardless of the tag.

Which model, and what it costs to run

Qwen3-32B

This job answers while someone waits, so latency comes first: we hold it to a single small card and, within that, take the best independent score on structured output and tool calls.

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.

Also in operations & logistics

All 13 →

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.