Every generation in StoryCraft AI consumes AI tokens. After each generation, the Review & Export panel shows a Token Usage section so you can see exactly how many tokens that run consumed.
For organisation-wide token monitoring, dashboards, and purchasing additional tokens, see the AI Usage & Tokens guide.
After every generation, a Token Usage section appears at the bottom of the Review & Export panel with three figures:
| Figure | What it measures |
|---|---|
| Prompt | Tokens sent to Monty (your input + configuration + system instructions) |
| Completion | Tokens Monty used to generate the output (stories, AC, test cases) |
| Total | Prompt + Completion — the total consumed by this single generation run |
Each Ask Monty message (create story, create sprint, create defect) consumes approximately 310 tokens. This is separate from story generation and is shown in the AI Usage & Tokens dashboard under your organisation's usage.
The Token Usage section is not visible
Token Usage only appears after a successful generation. If no stories were generated, the section will not show. Complete a generation run first.
Token usage seems unexpectedly high
Large input files (especially documents and videos) and Detailed complexity both drive up token counts. Try using Standard complexity or trimming the input source to the relevant sections.
Where can I see my total organisation token balance?
Open the AI Usage & Tokens dashboard from the sidebar or the billing area. It shows total balance, consumption by feature, and charts over time. See the AI Usage & Tokens guide for details.