Skip to main content
GPU compute is billed by the second on most GPUs (a few bill by the minute) while it runs. Every idle instance is wasted money.

Monitor your spend

Pick the right GPU

Delete instances when done

Use volumes to avoid re-setup costs

Re-downloading models wastes 10-30 minutes of GPU time per session:
Models and packages at /workspace/ persist across deploys.

Right-size your instance

Batch your work

Deploy, process, tear down: pay only for the minutes your job runs:

Use the Models API for light workloads

For light or bursty inference, the Models API bills per token, so you pay nothing while a GPU would sit idle:

Quick checklist

  • Run runcrate ps daily: kill anything not in use.
  • Run runcrate billing usage weekly: spot unexpected charges early.
  • Use volumes for models and data: avoid re-downloads.
  • Match GPU to workload: check nvidia-smi utilization.
  • Delete instances immediately after batch jobs complete.