Idle GPU Cost Calculator
A GPU left running idle bills exactly as much as one being used — this prices that out against live per-GPU $/hr rates, for the durations a box actually gets forgotten for.
What idle time actually costs
Cheapest live per-GPU rate for each model, times hours idle — the same rate you'd pay for that GPU in active use. Idle time is not discounted; a forgotten box bills at its full rate.
Try your own numbers
Idle auto-stop can remotely stop a box on this provider — this cost is what you'd avoid by turning it on, not what happens automatically (it's opt-in, and it needs a storage bucket configured first).
What actually stops this
Aquanode has an idle auto-stop feature that saves the environment and then stops the box after it's been idle past a threshold you set — but it is opt-in, not automatic everywhere. In the console it's pre-checked whenever you deploy with a storage bucket selected; through the API or the aq CLI it's off unless you turn it on explicitly. It also needs that storage bucket configured, since it saves the environment before it stops the box.
It works the same way on every provider Aquanode supports — idle auto-stop saves the environment then terminates the box, a create-and-terminate call every provider adapter implements, not a provider-specific stop API. There's no per-provider list to check before relying on it.
Resuming a paused box works the same way too: it rents a fresh box — here or on a different provider — and restores the snapshot onto it, so it isn't gated by which provider you paused on either. Restoring after a provider-side failure (spot reclaim, capacity loss) is only ever as good as a snapshot that was already scheduled before it happened — automated snapshots are opt-in and nothing schedules one at deploy time.
