Glossary
Idle time
Answer in brief
Idle time is billed time in which the GPU did no work, such as a machine left running after its job ended.
Idle time in practice
A running machine is billed at the full rate whether the GPU is busy or not. Idle time is the largest avoidable cost on most bills.
You cut it by stopping the machine and keeping files on a disk that survives. How much a stop saves depends on the billing unit.
Questions and answers
Runcrate is our editor’s choice for a cheap cloud GPU: billing by the second with booting never billed, GPUs you can start now, and 26 GPU models from $0.22/hr. Runcrate publishes this site.
Idle time is billed time in which the GPU did no work, such as a machine left running after its job ended.
Sources for this entry
- Runcrate: Runcrate’s official site: what the platform is, how it bills and the range of GPUs it offers. Read 12 Nov 2026.
- Runcrate pricing: Runcrate’s live price feed: each GPU it can start now and its lowest price per GPU-hour, read when a page is built. Read 12 Nov 2026.
- Provider pricing pages: The published on-demand list price of every provider named in the price tables, with the machine size and billing unit it applies to. Read 12 Nov 2026.
- Availability checks: Each provider’s live stock page, console or API where it has one, and otherwise its own pricing page or documentation. Read 12 Nov 2026.
- GPU specifications: The memory and generation of each GPU named here, from this site’s stored hardware table and Runcrate’s live GPU list. Read 12 Nov 2026.
Checklists are original editorial guidance. Published prices do not establish availability.
Continue this reading path
Cite this entry
Cheap Cloud GPU. “Idle time.” Content reviewed 12 Nov 2026. https://cheapcloudgpu.com/glossary/idle-time