Skip to main content
The Usage tab on your instance dashboard gives you a clear picture of how your AI assistant is being used and what you are spending.

​
Usage card

The usage card at the top of the Usage tab shows a summary for the current billing cycle:
MetricWhat it means
Messages sentTotal number of messages your assistant has received and replied to
Tokens usedTotal tokens consumed (input + output combined)
Estimated costYour accrued cost so far this cycle based on model pricing

​
Understanding tokens

AI models process text in units called tokens. As a rough guide:
  • 1 token ≈ 4 characters of English text
  • A short message (“What are your opening hours?”) ≈ 10–15 tokens
  • A detailed reply (300 words) ≈ 400–500 tokens
Both the messages sent to your assistant (input) and the replies it generates (output) count towards your token total.

​
Cost breakdown

Your bill is calculated as: 
Monthly base fee + (tokens used × per-token rate)
The per-token rate depends on the AI model you have selected. More capable models cost more per token. You can see a breakdown by model in the Usage tab.

​
Billing cycle

  • Your billing cycle starts on the date you first activated your instance.
  • You are charged monthly via the payment method on file.
  • An invoice is emailed to you at the end of each cycle.
Switching AI models mid-cycle is fine. Usage costs for each model are tracked separately, so your bill accurately reflects which model was used for which messages.

​
Setting a usage alert

To avoid unexpected charges, you can set a monthly usage alert from the Usage tab:
  1. Click Set alert next to the estimated cost.
  2. Enter a threshold (e.g. €50).
  3. Click Save.
You will receive an email notification when your usage reaches that amount.

​
Questions about your bill?

Email [email protected] with your account email and the billing period you are asking about.