ML Env

Use casesSales & B2B

A one-page brief on the prospect before the first call

Turns a prospect's website text, their enquiry and any public documents into a one-page brief, batch-prepared the evening before a call day.

How it works
You feed it the fetched text of the prospect's website, their enquiry, and anything public you have collected — a brochure PDF, a trade-register extract. The large model writes a one-pager: what the company does, likely fit with your offer, sensible questions to ask, and things not to embarrass yourself on. Briefs are batch-prepared the evening before a call day.
Data you need
The fetched text of the prospect's site and any documents you have. The model has no live internet access on your instance — someone or something must fetch the pages first; the model only reads what it is given.
What to expect
Quality is capped by what is public: a prospect with a three-page website yields a thin brief. The model may over-infer — 'they mention sustainability, so they'll want our eco line' is a useful hypothesis, not a fact — and websites go stale, so outdated facts get presented confidently. It offers no financial or credit judgement whatsoever.
Where people stay involved
The salesperson treats the brief as a starting point and verifies anything they plan to say out loud ('I saw you opened a plant in Gdańsk').

Which model, and what it costs to run

Qwen3-8B

This job runs in bulk rather than to a waiting person, so size is not the constraint — we take the strongest independent score on sticking to the document that we may serve freely and that fits on a single card.

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.

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.

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.

Phi-43.7% · answers 80.7%Llama 3.3 70B4.1% · answers 99.5%Gemma 3 12B4.4% · answers 97.4%Qwen3-8B4.8% · answers 99.9%Mistral Small 3.25.1% · answers 97.9%Granite 4.0 Small5.2% · answers 100%DeepSeek-V3.25.3% · answers 96.6%Qwen3-14B5.4% · answers 99.9%
Shorter is betterFree to serveConditions apply⚠ answered under 95%

Independent measurement · Vectara · board updated May 11, 2026

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.