AI Tokens and Limits

AI Tokens & Limits

AI usage in DocMgt is measured in tokens. A token is a small unit of AI work — roughly a fragment of a word — counted on everything the AI reads (input) and everything it writes (output). DocMgt tracks tokens so usage can be capped and reported.

Two monthly pools

End-User pool — capped by End User AI Limit
Builder pool — capped by Builder AI Limit

Both are configured under Admin > Main Options > AI and reset at the start of each calendar month. Each limit doubles as the on/off switch for its pool: you must enter a positive number to ENABLE that AI tier, and a value of 0 (or any value of zero or below) DISABLES it so no tokens may be spent. There is no "unlimited" setting — you always choose a deliberate monthly ceiling for each pool. Set each limit high enough to cover expected usage plus the base monthly tokens that come with your site, but keep in mind that a very large limit lets a rogue user or process consume a lot of tokens quickly.

Builder AI has no separate enable toggle — setting a Builder AI Limit greater than zero is what makes the Builder features (Edit & Build with AI, Create an E-form with AI, Create a Merge Template with AI, SOW Builder) available.

Workflow tokens are not limited in the same way as the End User and Builder tokens because they are process driven. If you need to monitor it programatically - use the [TOKENUSAGEWORKFLOW(From|To)] variable.

What happens when a limit is reached

The limit is checked at the start of each request. Once a pool is at or over its limit, new requests in that pool are refused with a message like: "AI token limit reached. You have a monthly limit of N tokens and have used N this month." Because the check happens up front, a request that starts just under the limit is allowed to finish even if it ends slightly over. A pool whose limit is 0 (or below) is disabled, so every request in that pool is refused.

Watching usage

Usage gauges appear next to many AI features and turn from green to yellow to orange to red as you approach the limit.

Token variables — [TOKENLIMITUSER()], [TOKENUSAGEUSER(From|To)], and related — let you display usage inside E-forms and documents. See AI Variables.

Usage reports — the AI usage report (AI Processing) breaks usage down by user, and the AI workflow report (AI Workflow) breaks down the automatic workflow AI actions.

Quality levels affect cost

Several AI features offer a quality choice (for example Economy / Balanced / Maximum on the extraction actions, or Balanced / Maximum on Auto-Annotate). Higher quality reads more carefully but costs more tokens. Each action's own help page describes its quality options.