# What is CPU overcommitment?

CPU overcommitment is promising more vCPUs to a host's machines than it has cores, betting that they will not all be busy at the same time.

**Runtime passes that bet back to you as a lower price. A shared sandbox has a
guaranteed floor, and you pay for the CPU it measures: $0.025 per active
vCPU-hour.** When a job needs its cores held at all times, `cpu: "reserved"`
keeps every vCPU for it. Those vCPUs are billed as always busy
([pricing](/docs/pricing)).

## How it works

A hypervisor schedules vCPUs onto physical cores the way an operating system
schedules threads. Most machines are idle most of the time. So a host with 16
cores can run guests with far more than 16 vCPUs between them, and still give
each one a core when it asks. The ratio of promised vCPUs to cores is the
overcommit ratio.

Linux does this with control groups. `cpu.weight`, from 1 to 10,000 with a
default of 100, sets a group's share when cores are contested. `cpu.max` sets a
hard ceiling: "the group may consume up to $MAX in each $PERIOD duration".
Kubernetes exposes the same pair as a container's CPU request and limit. It says
that at a limit "the kernel will restrict access to the CPU".

## Overcommitment done openly and quietly

| Approach                 | What you are told                | What you pay for            |
| ------------------------ | -------------------------------- | --------------------------- |
| Quietly overcommitted VM | "2 vCPUs"                        | 2 vCPUs, all the time       |
| Burstable instance       | A baseline and credits           | The instance, plus overages |
| Shared CPU on Runtime    | A floor, and bursts up to `vcpu` | The CPU the code measured   |
| Reserved CPU on Runtime  | Every vCPU, held                 | Every vCPU, busy or not     |

The honest version states the guarantee. On Runtime, that is the
[CPU floor](/glossary/cpu-floor): a twentieth of a vCPU by default, raised per
sandbox with `cpuFloorMillis`.

## Why it suits agents

An agent's sandbox waits on a model most of the time. Then it compiles or runs
tests for a few seconds. Sharing cores across many such sandboxes lets the
waiting cost $0.03125 an hour at 2 vCPUs and 4 GiB, instead of the full
$0.08.

## Related

- [Shared vs reserved CPU](/glossary/shared-vs-reserved-cpu)
- [What is a noisy neighbor?](/glossary/noisy-neighbor)
- [What is a vCPU?](/glossary/vcpu)
- [What are cgroups?](/glossary/cgroups)

## Sources

Checked 25 October 2026.

- [Control Group v2, CPU, the Linux kernel documentation](https://docs.kernel.org/admin-guide/cgroup-v2.html)
- [Resource management for pods and containers, Kubernetes](https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/)