Cloud sandboxes, measured

Oct 22 – Nov 9, 2026 · 10 providers (11 configs) · 2 caller locations: Florida, US & Frankfurt, DE · 100 runs per main test, 20 per location test

Oct 22 – Nov 9, 2026 · 10 providers (11 configs) · 2 caller locations: Florida, US & Frankfurt, DE · 100 runs per main test, 20 per location test

By location

How network distance changes latency: the same tests run from EU-Central (Frankfurt) and US-East (Florida).

Cold start by caller location

Median time from each caller location · Colored bar marks the faster location · Lower is better

Oct 26 – Nov 9, 2026 · 5–20 runs per test

E2BSandbox in Oregon
EU-Central
0.67 s
US-East
0.48 s
×1.4 faster from US-East
DaytonaAPI in Virginia
EU-Central
1.5 s
US-East
0.99 s
×1.5 faster from US-East
Upstash BoxSandbox in Virginia
EU-Central
3.0 s
US-East
2.5 s
×1.2 faster from US-East
BoatSandbox in Northern France
EU-Central
0.78 s
US-East
1.1 s
×1.5 faster from EU-Central
boxdSandbox in New York
EU-Central
0.49 s
US-East
0.29 s
×1.7 faster from US-East
FreestyleSandbox in SF Bay Area
EU-Central
1.1 s
US-East
0.81 s
×1.3 faster from US-East
TenkiSandbox in Seattle
EU-Central
1.1 s
US-East
0.91 s
×1.2 faster from US-East
SuperserveSandbox in Virginia
EU-Central
0.71 s
US-East
0.49 s
×1.5 faster from US-East
Vercel SandboxSandbox in Virginia
EU-Central
0.90 s
US-East
0.52 s
×1.7 faster from US-East
ModalSandbox in US East
EU-Central
1.1 s
US-East
0.36 s
×3.0 faster from US-East

Run a command

fastest location
E2B
0.12 sUS-East×1.5
Daytona
0.10 sUS-East×1.6
Upstash Box
0.22 sUS-East×2.5
Boat
0.11 sEU-Central×2.9
boxd
0.09 sUS-East×1.6
Freestyle
0.16 sUS-East×1.6
Tenki
0.17 sUS-East×1.4
Superserve
0.15 sUS-East×1.6
Vercel Sandbox
0.34 sUS-East×1.9
Modal
0.07 sUS-East×2.9

Write + read 10 MB

fastest location
E2B
1.3 sUS-East×2.1
Daytona
1.8 sUS-East×1.1
Upstash Box
2.1 sUS-East×1.9
Boat
3.5 sEU-Central×2.0
boxd
1.1 sUS-East×1.9
Freestyle
2.1 sUS-East×2.3
Tenki
2.0 sUS-East×1.5
Superserve
0.61 sUS-East×3.6
Vercel Sandbox
0.68 sUS-East×1.5
Modal
0.97 sUS-East×2.5

Agent tool replay

fastest location
E2B
14 sUS-East×1.6
Daytona
17 sUS-East×1.3
Upstash Box
21 sUS-East×1.8
Boat
23 sEU-Central×1.8
boxd
13 sUS-East×1.4
Freestyle
19 sUS-East×1.7
Tenki
15 sUS-East×1.6
Superserve
11 sUS-East×2.0
Vercel Sandbox
24 sUS-East×1.8
Modal
11 sUS-East×2.7

Boat (Northern France) runs its sandboxes in Europe; the remaining providers, boxd (New York) included, run in US-East. In-sandbox CPU, memory, disk, and package install speed do not change with caller location and are omitted here.

Cold start

Median s · lower is better

  • 1boxd: ran 4 vCPU, 16 GB, not 4 vCPU, 8 GB. boxd has no 8 GB size at 4 vCPU; this is its nearest.

Agent work, 100 tool calls

Median s · lower is better

  • 1boxd: ran 4 vCPU, 16 GB, not 4 vCPU, 8 GB. boxd has no 8 GB size at 4 vCPU; this is its nearest.

Quick task cost, per 1,000

Create, 100 tool calls, delete · USD · lower is better

Verified: eligible for the pickUnreconciled, provisional, unsettled or estimate: shown, not eligible

  • 1boxd: ran 4 vCPU, 16 GB, not 4 vCPU, 8 GB. boxd has no 8 GB size at 4 vCPU; this is its nearest.

Start from snapshot

Median s · lower is better

  • 1boxd: ran 4 vCPU, 16 GB, not 4 vCPU, 8 GB. boxd has no 8 GB size at 4 vCPU; this is its nearest.

Where the time goes

Step by step, from median timings, in each provider's own time.

TraceCold start · every provider, median of each step
Fastest
304ms
boxd · provider time
Slowest
2.62s
Upstash Box · provider time
Spread
8.6×
slowest vs fastest
Failures
0
of 1,100 attempts
Provider
0s1s2s3s
create()First commandRanked by provider time · pick a provider for its full trace.
TraceCold start · every provider, median of each step
Fastest
283ms
boxd · provider time
Slowest
2.62s
Upstash Box · provider time
Spread
9.2×
slowest vs fastest
Failures
0
of 1,100 attempts
Provider
0s1s2s3s
create()First commandOurs: Sandbox SDKRanked by provider time · pick a provider for its full trace.

Start-up

Cold start is the wait before an agent can do anything: from create() until the first command runs, the provider's own time.

Cold start

create() to first command, without our SDK's setup · Median seconds · Lower is better