Skip to main content

Control AI Analyst cost and privacy

You pay your AI provider directly, usually a few cents per analysis. These settings keep that predictable.

Keep costs low​

  • Monthly token limit: in AI Analyst → Settings, under the model. The box shows what the limit means in dollars, for example "500,000 tokens is about $0.80 a month". When it is reached, AI use stops until next month.
  • Cap per person: in Settings, Spending, set how many tokens each person may use a month. A person over the cap cannot ask until next month; nobody else is affected.
  • Answer reuse: the same question about the same data within a few hours shows the earlier answer again at no cost (Settings → Answer reuse, 6 hours by default, 0 turns it off).
  • No activity, no cost: when every figure is zero, the analyst says so without calling the AI model.
  • Reports first: when a Biznsbook report already answers the question, the analyst opens it instead of using AI.

Watch what it costs​

  • Runs and the overview show this month's analyses, tokens and cost; each brief shows its usual cost per run.
  • Usage (AI Analyst Managers) shows who uses it, cost per person, the most-asked questions, how often answers fail or are reused, and Reports instead of AI.
  • Spending alerts: AI Analyst Managers get an email when the model reaches 80 percent of its monthly token limit, and again when it reaches the limit.

Review who asked what​

  • Runs (or My runs) lists every analysis, including refused ones: when, the question, the kinds of data, the model and region, tokens and cost.
  • With the View AI Analyst Audit right you see everyone's runs.
  • Settings → History shows each time analysis was turned on or off, by whom, with which model and data.

:::info Biznsbook does not sell or look at your data Data goes from your company to the AI model you chose, on your own account. Biznsbook keeps only the answer and the tables in your company's own records. :::

Next step​