Couldn't load this page.

Fast & affordable sandboxes for AI agents

Get your agents working fast. Let them build in sandboxes and deploy persistent apps and databases.

npm install -g @lizard-build/cli
lizard sandbox create
Boot a sandbox from a template
lizard sandbox ssh
Shell in, no keys to set up
lizard sandbox exec
Run a command, stream the output
lizard sandbox files
Copy files in and out
lizard sandbox prompt
Run Claude Code or Codex
lizard sandbox expose
Public HTTPS URL for a port
lizard sandbox desktop
Full desktop in your browser
lizard sandbox pause/resume
Freeze state, resume later
lizard sandbox snapshot/restore
Save once, fork new sandboxes
lizard volume create
Disk that outlives the sandbox

Sandbox pricing

Pay as you go. No monthly subscription.

Set your workload

Sessions run back to back for a full month (730 hours).

Sandboxes at once
Session
CPU utilization
Resources per sandbox
Estimated monthly compute
$66 /mo

10 sandboxes × 730 hours × $0.009/h

Boat$1312×
Tensorlake$2654×
Cloudflare$4226.4×
Morph$4236.4×
Modal$4406.7×
Blaxel$4877.4×
Freestyle$71310.9×
Vercel$82612.6×
E2B$90713.8×
Daytona$91213.9×
CodeSandbox$96014.6×
Beam$1,65825.2×
Runloop$1,76426.8×

Sandbox egress is included up to 2 TB per account over a rolling 30 days. Read the limits

Everything your agents need to build.

Run code, keep files, preview apps, and monitor usage.

Sandboxes in the cloud

Run apps, databases, and background tasks. Use the tools you already know.

Persistent Volumes

Keep files between runs. Mount storage at /workspace.

Regional deployment

Launch in US East or EU West. Choose where your agent runs.

CLI or SDK

Use Lizard CLI in your terminal or Lizard SDK in your code.

Share a live preview

Preview your frontend over HTTPS. Share a link while your sandbox runs.

Observability

CPU and memory metrics. Logs and command output.

Give your agents a faster place to run.

Lowest median. Lowest average. Measured against E2B, Daytona, and Modal.

Lizard
196ms

Lowest median time

Less time is better

Full benchmark results

300 runs per provider. The lowest time in each column is highlighted.
ProviderMedianAveragep90p95p99Maximum
Lizard196 ms — Lowest time238 ms — Lowest time323 ms — Lowest time522 ms — Lowest time1,078 ms6,054 ms
E2B282 ms336 ms472 ms590 ms889 ms — Lowest time1,687 ms — Lowest time
Modal972 ms1,000 ms1,208 ms1,318 ms1,640 ms2,119 ms
Daytona977 ms1,063 ms1,436 ms1,611 ms2,547 ms6,441 ms

300 runs per provider. Median is the middle result; p90 means 90% of runs finished within that time. Rankings apply to this test.

AI sandbox FAQ

An AI sandbox is a separate place for an agent to run code, use tools, and work with files. Lizard Sandboxes let agents build, test, and debug in the cloud without running that code on your computer.

Sign in to Lizard, choose a project, and create a sandbox from a ready-made template. Choose base for shell tasks, codex for coding tasks, or interpreter for Python, then select a size and region.

Yes. Run Python scripts with the interpreter template, or use shell commands to run tools and tests. Read command output and save results to files. Each command starts a new process.

Lizard uses a pool of prepared Sandboxes to reduce setup time. Startup time depends on the template, size, region, and available capacity.

Each sandbox runs in its own Kubernetes pod using runc and shares the host kernel. It uses container isolation, without a separate virtual machine kernel. Give the agent only the credentials and access needed for its task.

You choose the lifetime when creating a sandbox, including no automatic expiry for longer tasks. A sandbox stops at its deadline even if a command is running. Commands do not extend the deadline, and idle time does not stop it early.

Yes. Attach Persistent Volumes at /workspace to keep files after a sandbox stops and reuse them in later runs. A volume connects to one sandbox at a time. Storage stays on one node, so export files you need to protect against node loss.

Yes. With access to your project, an agent can deploy apps and databases through Lizard CLI. They run as separate resources on Lizard and keep running after you stop or delete the sandbox.

Yes. Create a separate sandbox for each task so agents can run commands and tests at the same time. The number of Sandboxes you can run depends on your account limits and available capacity in the region.

The Small size costs $0.009/hour for 2 vCPU and 4 GB RAM. Billing runs by the second, including idle time, with CPU, RAM, and sandbox egress included. Persistent Volumes cost extra. Older sandboxes without a size keep their original usage-based billing.

Trial or promo credits, when available in your account, can cover Sandboxes usage. Standard accounts use pay as you go with no monthly subscription. Trial and promo credits can expire; purchased credits do not.

Build with AI. Ship with Lizard.

You don't need a platform team to go live. Your whole cloud, one CLI command away.

Try for free
Services
—
Add-ons
—
Deployments
—
Sandbox starts
—

We use cookies for essential site functionality and analytics. See our Cookie Policy.