Beam
https://www.beam.cloud/sandbox
Beam Sandboxes are isolated compute environments that AI agents or their harnesses control to run untrusted or LLM-generated code. They expose process execution, filesystem transfer, and dynamically exposed ports, and accept custom container images, GPUs, and persistent storage volumes. The product is used by teams building AI coding agents, inference workloads, and tool-using assistants that need fast, ephemeral execution environments.
| Pricing model | Per-second, billed on CPU cores, RAM, and GPU while the sandbox is running; idle sandboxes cost nothing. |
|---|---|
| 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. | Per-second/per-millisecond billing for CPU, RAM, and GPU (see pricing page for per-unit rates) |
| 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. | 1–3 s cold boot; container start under 1 s |
| Max runtime The longest a sandbox may run. | – |
| Isolation The isolation technology between sandboxes. | gVisor + runc |
| GPUs Whether GPU instances are available for sandboxes. | ✓ |
| Docker Whether Docker containers can run inside the sandbox. | ✓ |
| SDKs | Python, TypeScript |
✓ yes · ✕ no · – no cited public fact.
Beam's managed cloud and the self-hosted open-source Beta9 share the same API, but the public pricing page lists both per-second sandbox rates and on-demand hourly GPU rates that differ; verify which tier applies to your workload.
Sources
- https://docs.beam.cloud/v2/environment/custom-registries
- https://docs.beam.cloud/v2/reference/py-sdk
- https://docs.beam.cloud/v2/reference/ts-sdk
- https://pypi.org/project/beam-client/
- https://docs.beam.cloud/v2/topics/cold-start
- https://docs.beam.cloud/v2/sandbox/overview
- https://docs.beam.cloud/v2/sandbox/snapshots
- https://beam.cloud/sandbox
- https://www.beam.cloud/sandbox
- https://docs.beam.cloud/v2/sandbox/configuration
- https://docs.beam.cloud/v2/resources/pricing-and-billing
- https://docs.beam.cloud/v2/sandbox/networking
- https://beam.cloud/pricing
- https://www.beam.cloud/
- https://www.beam.cloud/blog/how-to-self-host-code-sandbox
- https://github.com/beam-cloud/beam-client
Last verified 2026-08-18. Corrections land through the update log.