StateSet Sandboxes
https://stateset.com/sandboxes
StateSet Sandboxes, also called Agent Cloud Runtime, is a cloud-computer runtime for AI agents that runs code, browsers, desktop GUIs, REPLs, and autonomous sessions in isolated sandboxes. Each workload gets an isolated environment with checkpoints, controlled networking, warm pools, and a choice of five isolation boundaries. The product ships with built-in RBAC, quotas, metering, audit logs, metrics, and tracing.
| Pricing model | – |
|---|---|
| Pricing The headline compute price as the provider states it. Sorting ranks prices stated per vCPU over time, converted to hourly. Other pricing models sort after, unranked. | – |
| Free while idle Whether a stopped, paused, or sleeping sandbox costs nothing. | – |
| Elastic Resources flex with what the sandbox actually uses, and the bill follows: yes when the provider bills on active or observed use, no when capacity is reserved or allocated and billed while it runs. | – |
| Memory snapshots Whether RAM state survives a pause and resume, not just disk. | – |
| Wake on request Whether a stopped sandbox wakes automatically on inbound traffic. | – |
| Start / resume Typical time from create or resume to running. Sorting ranks stated times, converted to seconds; claims with no figure sort after, unranked. | – |
| Max runtime The longest a sandbox may run. | – |
| Isolation The isolation technology between sandboxes. | Container, gVisor, Kata, Firecracker, or WASM (selectable per workload) |
| GPUs Whether GPU instances are available for sandboxes. | – |
| Docker Whether Docker containers can run inside the sandbox. | – |
| SDKs | – |
✓ yes · ✕ no · – no cited public fact.
No pricing is published on the product page.
Sources
Last verified 2026-09-03. Corrections land through the update log.