How AI calls are billed

Two parts, in two currencies

Every AI call is charged as:

general credits for the call  +  AI credits for the tokens

The base is a fixed number of general credits, reserved before the call runs. The token charge is in AI credits, added afterwards — because nobody, including us, knows how many tokens a model will use until it has finished.

This split is not bookkeeping. AI credits pay for what a provider charges us; general credits pay for everything else. A workspace with general credits and no AI credits can run every tool except the ones that call a model.

A summarising call, for example, reports:

credits: 10 — 8 general + 2 AI

What a token is

A token is roughly four characters of English. A 1,000-word document is around 1,300 tokens. Both directions are counted:

• Input tokens — everything sent to the model: your text, our instructions, and any instructions you have saved.
• Output tokens — what the model writes back.

Output is the expensive half. Every provider charges several times more for it, so the single biggest lever on what a call costs you is how long an answer you ask for.

What the rates are

Every model sits on a tier, and the tier sets the rate. Rates are in AI credits:

The tier is shown wherever you choose a model, so you always know what you are agreeing to before a call runs. Output costs more than input on every tier because it costs more to produce — that is why asking for a shorter answer is the most effective way to spend less.

Embedding models charge for input only. There is no generated output, so the cost of an embedding call is entirely predictable from what you send.

These rates are set in the admin catalogue and can change; the table wherever you pick a model is always the live one.

Bringing your own key

If you add your own provider key, you pay that provider directly and we do not charge AI credits for tokens at all. What remains is a small general-credit fee for routing, retries and the credential handling — our costs, not theirs.

The ceiling

Every AI tool has a maximum credits per call. If a call somehow exceeds it, you are charged the maximum and not a credit more — we absorb the difference. You will never receive a surprise bill from a single request.

Keeping the cost down

1. Ask for shorter output. The summary-length control on the web tool, or maxLength over the API.
2. Send less. Trim the input to what the model actually needs to see.
3. Drop a tier. Economy handles summaries, extraction and classification well; Premium is for work where the answer has to be right.
4. Bring your own key if you already have provider credit.