Home / AI agent sandboxes / NVIDIA OpenShell / Pricing
NVIDIA OpenShell pricing
In short (2026-11-13): No hourly price published. Free tier: Free open-source software under the Apache-2.0 license. Source: official pricing page. Prices checked 2026-11-15.
Usage rates
- Storage
- No separate monthly rate published
- Billing
- Not applicable: free software run on your own infrastructure. Not applicable: you pay only for your own hardware or cluster
Billing details that change the bill
- Stop and start keep the sandbox's persistent workspace, policies and settings, but not process memory.
- The microVM driver is opt-in and is never auto-detected; without it, sandboxes are containers.
- On Kubernetes, the cluster network plugin must enforce NetworkPolicy, or sandbox pods can bypass OpenShell network policy.
- The project collects anonymous telemetry by default; it can be turned off.
Price history
No price change found since we started tracking on 2026-11-13. We check every pricing page daily.
Cheaper or better-fit NVIDIA OpenShell alternatives →
Sources
- https://github.com/NVIDIA/OpenShell, checked 2026-11-13:
OpenShell is the safe, private runtime for fleets of autonomous AI agents.
- https://github.com/NVIDIA/OpenShell, checked 2026-11-13:
Agents never see real credentials; OpenShell adds them only to requests bound for approved endpoints.
- https://github.com/NVIDIA/OpenShell, checked 2026-11-13:
This project is licensed under the Apache License 2.0.
- https://docs.nvidia.com/openshell/latest/how-it-works/sandboxes/runtimes, checked 2026-11-13:
When compute_driver is unset, the gateway auto-detects Kubernetes, then Podman, then Docker. The VM driver is never auto-detected.
- https://docs.nvidia.com/openshell/latest/how-it-works/sandboxes/runtimes, checked 2026-11-13:
The MicroVM driver runs each sandbox in its own lightweight VM. It requires host virtualization: Apple Hypervisor on macOS or KVM on Linux.
- https://docs.nvidia.com/openshell/latest/how-it-works/sandboxes/overview, checked 2026-11-13:
To request GPU resources, add --gpu
- https://docs.nvidia.com/openshell/latest/how-it-works/sandboxes/overview, checked 2026-11-13:
Stop compute when you want to retain a sandbox and its persistent workspace without keeping its container, pod, or VM running
- https://github.com/NVIDIA/OpenShell/releases/tag/v0.1.8, checked 2026-11-13:
v0.1.8