Draft the job ad from a five-line brief

Turn a five-line role brief and a couple of past ads into a structured job-ad draft in your company's tone, ready for the hiring manager to edit.

How it works: You give a bullet-point brief — role, must-haves, salary band, location, contract type — plus one or two past ads so the draft sounds like your company. The large model produces a structured draft: intro, responsibilities, requirements, what you offer. You then iterate on tone and length by asking for changes, instead of starting from a blank page.
Data you need: A role brief from the hiring manager and ideally two or three previous job ads for tone. Include the salary range in the brief — the EU Pay Transparency Directive is bringing pay information into recruitment across member states, though exact national rules vary; check your local requirements.
What to expect: A solid first draft that gets the structure right and stays close to the tone of your past ads. Without your own examples the output sounds like every AI-written job ad on the internet — generic and slightly too enthusiastic — and if the brief is thin the model will happily invent perks you do not offer. Watch for subtly exclusionary phrasing ("young dynamic team", "native speaker"), which the model can reproduce from its training data; that discrimination risk is yours to catch, not the model's.
Where people stay involved: The hiring manager rewrites and approves every ad. Legal wording — equal-opportunity statements, local requirements — is a human check, because the model does not reliably know your country's rules, and it does not know your actual team.

Which model, and what it costs to run

Qwen3-8B

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 sticking to the document.

Licence: Apache-2.0
Weights at 4-bit: 5 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: $0.04 / $0.04per M in / out · DeepInfra

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.

Sticking to the document

Vectara Hallucination Leaderboard · HHEM · 17 of 18 models measured

Measured on public documents, by a model acting as judge. Read it beside the answer rate: the lowest hallucination rates on this board belong to models that simply decline more often.

Shorter is betterFree to serveConditions apply⚠ answered under 95%

Independent measurement · Vectara · board updated May 11, 2026

Reading a long document whole

No benchmark measures this

No current benchmark ranks today's open models here. HELMET showed that the popular test — finding a planted sentence — predicts nothing, and its own table has not been rerun on 2026 models.

So we do not show a chart here. We measure it on your own content, in the first week, and you see the result before anything ships.

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 hr & internal

All 14 →

Draft the job ad from a five-line brief

Qwen3-8B

Sticking to the document

Reading a long document whole

The API is cheaper per token. Here is why our customers don't use it.

Also in hr & internal

Let staff ask the handbook a question instead of asking HR

Give every new starter an onboarding buddy that never gets tired of questions

Search the shared drive by meaning, not by remembering the filename

Build a structured interview guide from the job description

Tell us what your team does by hand