Leap0 vs Runtime
Choose Leap0 for trying a full-featured microVM sandbox (desktop, LSP, git, snapshots) at no cost while it is in public preview; choose Runtime for cost-sensitive agent workloads with many short runs, where active-CPU billing and a free monthly allowance matter. Leap0 uses Firecracker microVM isolation; Runtime uses Firecracker microVM isolation.
Key differences between Leap0 and Runtime
- Session length: 8 h max (Leap0) versus No limit documented (Runtime).
- SDKs and interfaces: Only Runtime lists Ruby, Java, CLI and REST API.
What they have in common
- Both are hosted platforms.
- Both use microVM isolation.
- Neither is open source.
- Both support snapshots.
- Both can pause and resume a sandbox.
- Both list Python, TypeScript, Go and MCP server.
Leap0 vs Runtime at a glance
| Attribute | Leap0 | Runtime |
|---|---|---|
| What it is | Firecracker microVM sandboxes in public preview, free during preview, with memory snapshots, forks, a per-sandbox firewall with credential-injecting header transforms and an XFCE desktop. | Firecracker microVM sandboxes billed on active CPU at $0.025 per vCPU-hour, with pause that keeps memory, forks, SDKs in five languages and no plan fee. |
| Type | Hosted platform | Hosted platform |
| Isolation | Firecracker microVM with a dedicated Linux kernel per sandbox; the VMM process is jailed with chroot, cgroup v2, seccomp filters and unique UID/GID pairs | Firecracker microVM with its own Linux kernel, disk and memory per sandbox, on dedicated servers Runtime operates |
| Open source | No | No |
| Self-host / BYOC | Not documented / Yes | Not documented / Not documented |
| SDKs | Python, JavaScript/TypeScript, Go, MCP server | JavaScript/TypeScript, Python, Go, Ruby, Java, CLI, REST API, MCP server |
| Cold start (vendor claim) | Website: "Sandboxes boot in around 100ms" (vendor claim) | Runtime measures create and exec from outside every one to five minutes and publishes p50/p95/p99 on its speed page; the September 2026 figures were taken down on 27 October 2026, so no current figure is published |
| Max session | Sandbox timeout from 1 minute to 8 hours, default 5 minutes; limits may change during the public preview | No maximum documented; a sandbox pauses itself after 300 seconds of inactivity by default (idlePauseSeconds 60–86,400, or 0 for never) |
| Persistence | Point-in-time snapshots of a running sandbox including in-memory state and writable disk; pause, snapshot and resume across sessions; fork one snapshot into many parallel sandboxes; 10 GiB disk per sandbox | Pause keeps memory and processes; paused sandboxes are kept while the account has credit or for 1–365 days as set (30 days after credit runs out with a card or prior top-up, 7 days otherwise); snapshots of running or paused sandboxes; forks of 1–10 running copies with memory and processes; volumes backed up daily; S3, R2 and GCS bucket mounts |
| Snapshots / pause | Yes / Yes | Yes / Yes |
| GPU | Not documented | Not documented |
| Networking | Per-sandbox firewall with domain allowlists, CIDR rules and header transforms that inject secrets outside the sandbox; demo shows outbound TCP blocked and DNS restricted by default; HTTP/SSE/WebSocket access to apps inside the sandbox | Per-sandbox allow and deny lists, or internet off; sandboxes reach only the public internet, private addresses refused; HTTPS previews on runtimehost.com (private by default with rotatable tokens), custom domains, public TCP ports, WireGuard private networks and a dedicated outbound IPv4 ($5 per 30 days); secrets substituted by the host on outbound requests |
| Pricing | Free during public preview. Rates to apply when billing goes live: $0.0504 per vCPU-hour ($0.000014 per second) and $0.0162 per GB-hour ($0.0000045 per GB-second) | $0.025 per active vCPU-hour and $0.0075 per reserved GiB-hour, billed per second; a waiting sandbox bills memory plus a 0.05 vCPU floor; paused sandboxes, snapshots and images $0.08 per GB per 30-day month; volumes about $0.11 per GiB per 30 days; outbound traffic free to 100 GiB a month then $0.02 per GB; no plan, seat or minimum fee |
| Free tier | Free during public preview, no credit card required | 100 free hours of a 1 GB machine (100 GiB-hours of memory, 25 vCPU-hours of active CPU) in the first 30 days with no card, renewing monthly once the account has paid; without credit up to 4 sandboxes at once of 2 vCPU and 4 GiB |
| Compliance | Not documented | No certification of Runtime itself is named; the trust page lists subprocessor attestations (Virginia data centre SOC 1/2/3 Type 2 and ISO 27001; Neon and Vercel SOC 2 Type 2); DPA included in every account; SAML/OIDC SSO and SCIM free; 99% monthly API uptime promise on paid accounts |
| Regions | United States only; more regions planned | All processing in one region in Virginia, United States (trust page); limits are counted per region |
| Company headquarters | Not documented | Denver, Colorado, United States |
| Good fit for | Trying a full-featured microVM sandbox (desktop, LSP, git, snapshots) at no cost while it is in public preview | Cost-sensitive agent workloads with many short runs, where active-CPU billing and a free monthly allowance matter |
Verified November 14, 2026 from each provider’s documentation. Cold-start figures are vendor claims, not our measurements.
Which should you choose?
Reasons to choose Leap0
- You want to evaluate a microVM sandbox with desktop, LSP and git support at no cost.
- You need memory-inclusive snapshots and forks for parallel exploration.
- You want outbound secrets injected by the firewall rather than placed in the sandbox.
- You run computer-use agents and want a ready XFCE desktop with recording.
Reasons to choose Runtime
- You want the lowest published per-vCPU rate with billing only for active CPU.
- You need SDKs in Go, Ruby or Java as well as Python and TypeScript.
- You want SSO, SCIM, audit logging and a DPA without an enterprise contract.
- You run many short agent jobs and want a renewing free monthly allowance.
Trade-offs to check first
- Leap0: Public preview with explicit warnings of breaking changes and downtime; billing not yet live.
- Leap0: US region only; sessions capped at 8 hours.
- Runtime: Single region: everything runs in one region in Virginia, United States.
- Runtime: No startup latency figures are currently published, and no certification of Runtime itself is named.
Both are worth piloting with your own image and region. See the full Leap0 profile and Runtime profile, or the complete comparison.
More comparisons
Frequently asked questions
Is Leap0 or Runtime better for AI agents?
What is the difference between Leap0 and Runtime?
Which is open source, Leap0 or Runtime?
How do Leap0 and Runtime isolate code?
How does Leap0 pricing compare with Runtime?
How long can sessions run on Leap0 and Runtime?
idlePauseSeconds 60–86,400, or 0 for never).Do Leap0 and Runtime support snapshots or pause and resume?
Sources
Check before you rely on it. Products change quickly, and this page reflects public documentation as of November 14, 2026. Confirm anything that matters in the provider’s own documentation.
Cite this page
Agent Sandboxes. (2026). Leap0 vs Runtime. agentsandboxes.org. Last reviewed November 14, 2026. https://agentsandboxes.org/compare/leap0-vs-withruntime/