Skip to content

Between you and the model

Describe the outcome.
We handle the prompt.

Write what you need in plain words. CALEST works out the rest and gives you something you can use.

€5 free once you confirm your email. No card, no subscription.

calestai.com/app

Break down our revenue for the first half.

Revenue, January to June

Revenue held steady across the six months, with a clear spike in March. Two things stand out:

  • 1.March runs well above every other month.
  • 2.May drops back while customer count holds.
Model chosen automatically€0.002

AI is capable. Using it well is still work.

Good answers need good questions.

Most people never learn the trick. The model could do more; it just never gets asked properly.

Nobody knows which model to use.

There are dozens. They change every month. Today that choice is yours to make.

Missing detail gets invented.

Leave a gap and a model fills it in silently. Nothing in the answer tells you which parts were guessed.

How it works

You describe it. We do the rest.

  1. You write it down

    One or two sentences. In your own words, the way you'd say it out loud.

  2. CALEST works it out

    It reads the task, settles what's missing, and routes the work.

  3. You get something usable

    A finished piece of work, with what it assumed and what it cost.

Desktop

Immer einen Tastendruck entfernt.

CALEST

Break down our revenue for the first half.

Reading the task …
Model chosen automatically€0.002
CALEST

Break down our revenue for the first half.

Revenue, January to June

Revenue held steady across the six months, with a clear spike in March. Two things stand out:

  • 1.March runs well above every other month.
  • 2.May drops back while customer count holds.
Model chosen automatically€0.002
CALEST
Q2 revenue review2 min ago
Find duplicate rowsYesterday
Decline a vendorYesterday
Plan the office moveMonday
Model chosen automatically€0.002

Get something you can use.

What you get.

It reads what you meant

Even from one line. Anything important that's missing gets filled in — and shown to you, not hidden.

It picks the model

Every task goes to the model that suits it. You never have to know the names or make the call.

You see what it cost

Every request shows its price the moment it finishes. Simple work never runs on expensive models.

The same ask gives the same answer

Tomorrow, and after the models underneath have changed.

For developers

Change one line.

CALEST speaks the API your tools already use. Point them at a different address and carry on.

anfrage.py
from openai import OpenAI client = OpenAI(    base_url="https://api.calest.dev/v1",    api_key="clst_...",) answer = client.chat.completions.create(    model="calest",    messages=[{"role": "user", "content": "Break down our revenue for the first half."}],)
antwort.json
{  "choices": [{    "message": {      "role": "assistant",      "content": "Total revenue €8,731; monthly average €1,455 …"    }  }],  "usage": { "total_tokens": 963, "cost_eur": 0.0018 }}

Security

Your work stays yours.

What a tool does with your input shouldn't take a search to find out. So it's here, not only in the privacy policy.

  • Encrypted end to end

    TLS in transit, encrypted at rest.

  • Never used for training

    Not by us, and not by the providers behind us.

  • Yours to delete

    Remove a conversation, or the whole account, whenever you want.

  • Priced in the open

    Every request shows what it cost. Nothing shows up later.

Pricing

Start with €5 on us.

Confirm your email and €5 lands in your account. Top up €10 later and we'll add another €5. No card to start, no subscription, ever.

How far €5 goes

You pay for what you use, not per request. A short question costs a fraction of a cent; a long report costs more. Roughly:

  • ~1,000

    quick asks

    Questions, rewrites, short pieces of text

  • ~200

    real work

    Analyses, drafts, longer answers

  • ~40

    heavy lifting

    Documents, reports, a lot of context

Ballpark figures, not a promise. The real cost of every request is shown next to its answer.

When you need more

Top up whatever you like. Credit never expires and isn't tied to a plan.

  • €10

    + €5 bonus on your first top-up

  • €25

    Most people land here

  • €50

    For daily use

Building something of your own? The same access is available through the API, on the same credit, with no base fee.

Questions

What can I do with the €5?

Everything. Nothing is locked behind a paid tier and no trial runs out — the credit only goes down when you actually use it.

Do I need a card to start?

No. Confirm your email address and the credit is yours. A payment method only comes up if you decide to top up later.

Which AI model is behind it?

Several. CALEST picks the one that fits each task. You can see which one answered, but you never have to choose.

Is this just another chatbot?

No. CALEST takes the outcome you want, settles what's missing first, and only then does the work. The difference shows most when a request is incomplete.

Does it make things up?

Less. Specific claims have to come from something you provided, and assumptions are shown rather than quietly made. It's still a language model — check anything that matters.

What happens to what I type?

It's used to do your work and kept with your account so you can find it again. It is never sold or handed to anyone for training.

Building with the API? The documentation covers the technical side.

Get on with the work.

€5 in credit once you confirm your email. No card, no subscription.