How billing tokens work
What a token is, what spends them, and what happens when your plan runs out.
On this page
How billing tokens work
Monokrew uses tokens as a single unit for everything you do — chatting, coding, generating media, running workflows. This keeps costs transparent: one balance, spent as you work, visible in real time.
Your token balance
Your balance is shown in the navigation bar and updates live as you work. When you start a job, the tokens it's expected to cost are held, so your available balance reflects both what you've spent and what's currently reserved. This prevents overspending — you can't start work you can't cover.
How tokens are spent
When you submit a job, a hold is placed against your balance. When the job finishes, the actual cost is settled — the hold is released and your real usage is deducted, so your balance reflects the true cost of the run right away. Different kinds of work cost different amounts: a short chat costs little, while generating a video or running a long coding session costs more.
Watching a run
For longer runs, the coding execution screen shows tokens counting down in real time, along with the rate. If a run approaches zero, it pauses cleanly rather than failing partway through, and you can top up and resume where you left off.
Getting more tokens
Your plan includes a monthly token allowance. If you need more, you can purchase additional tokens at any time — the balance updates as soon as the purchase completes. Running low is handled gracefully: you'll be prompted to top up before work is blocked.
Seeing where tokens went
Your consumption view breaks spend down by job, so you can see what each piece of work cost. This makes it easy to understand your usage and plan ahead.
Plans and tiers
Different plans come with different monthly allowances and resource limits. Choose the tier that fits your usage; you can change plans as your needs grow.
Something missing or wrong? Tell us.