Morph Cloud vs Deno Sandbox

Morph Cloud gives each agent a full VM that can be paused, branched and woken with its memory, and it stays up as long as you want. Deno Sandbox gives short, locked-down runs in a 2 vCPU microVM that starts in under 200 ms and lives up to 30 minutes.

The companies and products

Morph Cloud

Morph Cloud sells full virtual machines for AI agents that can be snapshotted, branched and restored with their memory, which it calls Infinibranch.

You get MorphVM instances as low-level building blocks and Devboxes as ready workspaces on top of them, with SSH, preview URLs and a tmux API for running coding agents you install yourself. Everything is billed in MCUs, where one MCU is 1 vCPU, 4 GB of RAM or 16 GB of disk for an hour. It is built for teams that fan agents out from one saved state, and it also sells managed GitHub Actions runners and a shared filesystem.

Deno Sandbox

Deno Sandbox is part of Deno Deploy, the hosting platform from the company behind the Deno runtime, and runs untrusted or AI-generated code in Linux microVMs.

Each sandbox is a Firecracker microVM with 2 vCPU, up to 4 GB of memory and a 10 GB disk that is wiped when it ends, created from a TypeScript or Python SDK. Outbound traffic goes through a proxy that can enforce a host allowlist and swap placeholder secrets for real ones. It is built for short runs of agent or user code, and a sandbox can be promoted to a Deno Deploy app.

Which use cases each one fits

For each use case, Battleships prices every sandbox provider on the same workload and sorts them from the cheapest monthly bill up. “16th cheapest of 345” means 15 of the other 344 providers run that workload, with every feature it needs, for less. “With limits” means the provider runs it but misses something, so it is listed after every full match. Open a use case for its whole ranking and what each provider misses.

Use case and its workloadMorph Cloud: price rankDeno Sandbox: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Long builds with Docker outlast Deno's 30-minute lifetime and 2 vCPU shape; Morph runs them in a full VM, and boat adds preinstalled coding agents you steer by API.
198th of 367, with limits
$2,288 a month
290th of 367, with limits
$5,665 a month
3rd cheapest of 367
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An assistant that lives on its machine all month fits Morph's VMs, not Deno's 30-minute sandboxes; boat adds a desktop and a credentials proxy for any API.
235th of 366, with limits
$3,014 a month
287th of 366, with limits
$5,803 a month
5th cheapest of 366
$657 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
Both suit short code runs: Deno starts in under 200 ms and bills CPU only while code runs, and Morph can pause a VM with its memory and wake it on the next request.
16th cheapest of 345
$154 a month
141st of 345, with limits
$329 a month
186th of 345, with limits
$2,000 a month
Sandboxes for your users
300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month
Morph fits this one and can wake each user's paused VM on request, while Deno Builder allows 20 sandboxes at once per region; boat gives each user token-protected HTTPS on up to 50 ports.
12th cheapest of 361
$905 a month
148th of 361, with limits
$1,863 a month
Cheapest of 361
$209 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
Morph's memory branching suits rollouts that all start from the same running state, which Deno cannot do because it has no fork of a running sandbox.
86th of 360, with limits
$4,847 a month
122nd of 360, with limits
$7,963 a month
34th of 360, with limits
$2,000 a month
Agent evals
250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month
38th cheapest of 364
$675 a month
296th of 364, with limits
$1,563 a month
10th cheapest of 364
$200 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
Morph sells managed GitHub Actions runners, Deno does not document Docker inside a sandbox, and on boat you run your own runner with Docker and /dev/kvm.
39th cheapest of 377
$355 a month
304th of 377, with limits
$731 a month
4th cheapest of 377
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
A dev box that stays on all month works on Morph and boat, while a Deno sandbox ends after 30 minutes and wipes its root disk.
85th cheapest of 368
$116 a month
179th of 368, with limits
$200 a month
18th cheapest of 368
$26 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
Neither Morph nor Deno ships a browser and computer use API; boat has a 60fps desktop with Chromium and a computer use API in every sandbox.
182nd of 369, with limits
$595 a month
280th of 369, with limits
$1,583 a month
6th cheapest of 369
$200 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
214th of 367, with limits
$250 a month
284th of 367, with limits
$783 a month
7th cheapest of 367
$200 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
239th of 346, with limits
$234 a month
286th of 346, with limits
$573 a month
6th cheapest of 346
$90 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
154th of 338, with limits
$4,750 a month
247th of 338, with limits
$11,923 a month
71st of 338, with limits
$1,800 a month
Parallel red teaming
200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month
214th of 360, with limits
$228 a month
251st of 360, with limits
$367 a month
2nd cheapest of 360
$200 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
Can't run itCan't run itCan't run it
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Can't run itCan't run itCan't run it

Key features

FeatureMorph CloudDeno Sandboxboat
IsolationFull VM with its own kernelFirecracker microVM with its own kernelFull VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Machine sizeYou pick vCPU, RAM and disk; account pool of 64 vCPU / 256 GB on Developer, up to 1,024 vCPU / 4,096 GB on Scale2 vCPU fixed, 768 MB to 4 GB memory, 10 GB disk4 vCPU / 8 GB by default, up to 16 vCPU / 32 GB on the $100 plan and above
Session lengthNo expiry unless you set a time to liveUp to 30 minutes; longer work can be promoted to a Deno Deploy appNo cap on paid plans; you set the time to live
Disk that persistsKept when you pause or snapshot; a plain stop deletes the instanceRoot disk wiped when the sandbox ends; opt-in volumes of 300 MB to 20 GB, Chicago onlyWhole disk saved every minute and on every stop; a stopped sandbox is free
Pause and fork with memoryPause with memory, and branch a running VM into many copies in under 250 msNo pause and no fork; read-only volume snapshots that new sandboxes boot fromFork a running sandbox with its disk; no memory snapshot
Wake on requestA paused VM resumes on the next HTTP request, SSH or exec callNoNo; a stopped sandbox is started by API
Docker and nested virtualizationRoot, Docker and systemd; nested virtualization is experimentalRoot access; Docker and nested virtualization not documentedDocker, systemd and /dev/kvm for Android emulators and VMs
Start timeRestores a snapshot in under 250 msUnder 200 msBoots a full VM
Desktop and browserBrowser-based remote desktop; you install the browser and any computer use agentNo desktop; a VS Code editor in the browser and SSHLinux desktop streamed at 60fps, with Chromium and a computer use API
Coding agentsYou install the agent and drive it through a tmux API that sends keys and reads the screenA root image with Claude Code, run through the shell command APISeven agents preinstalled, with a prompt, steer and events API
Keeping API keys out of the sandboxResponses Proxy for model APIs only; other secrets are handed to the machinePlaceholder secrets swapped for real ones on requests to approved hostsCredentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Outbound rulesOpen internet; no host allowlist documentedHost allowlist per sandbox, enforced by a proxy outside the VMOpen internet, no provider-side allowlist
Inbound accessNamed HTTP services with optional API key auth; SSH through Morph's gateway; no raw TCPHTTPS URL per exposed port, public without authentication; SSHHTTPS URLs for up to 50 ports, token-protected by default; raw TCP
Regions and guest systemsRegions not published; Linux, with experimental Windows and macOS (x86)Amsterdam and Chicago; LinuxEU only (Germany, Finland, France), with zero data retention; Linux
Every feature Battleships tracks (43)
FeatureMorph CloudDeno Sandboxboat
Full VM (own kernel)YesYesYes
Docker insideYesNot publishedYes
Nested virtualizationYesNoYes
RootYesYesYes
SystemdYesNot publishedYes
Desktop GUIYesNoYes
BrowserNoNoYes
Computer-use APINoNoYes
SSHYesYesYes
Persistent diskYesYesYes
Pause/resumeYesNoYes
Automatic snapshotsYesNoYes
Fork/cloneYesNoYes
Live fork (no pause)YesNoYes
Memory forkYesNoNo
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesNoYes
Idle auto-stopYesNoNo
Wake on requestYesNoNo
HTTPS preview URLsYesYesYes
Raw TCP inboundNoNoYes
Public IPv4NoNoNo
Egress allowlistNoYesNo
Secret proxyYesYesYes
Secret proxy for any APINoYesYes
Preinstalled agentsNoYesYes
Agent harness APIYesNoYes
MCP serverNoNoNo
GPUNoNoNo
WindowsYesNoNo
Arm64NoNoNo
Self-hostingNoNoNo
BYOCNoNoNo
Open sourceNoNoNo
Scoped API keysYesNot publishedYes
Spend limitsNot publishedYesYes
Usage per sandbox (API)YesNoYes
Audit logsYesNot publishedNo
SSONot publishedNoNo
SOC 2Not publishedYesNo
HIPAANot publishedYesNo
EU data residencyNot publishedYesYes
Zero data retentionNot publishedNot publishedYes

Performance

Morph CloudNot measured
Deno SandboxNot measured
boat26.69 runs/s

There is no comparable CPU measurement for Morph Cloud or Deno Sandbox: neither is in the StarSling hpc-sandbox-benchmarks run. boat did 26.69 runs per second on that Node.js build-and-test loop at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts. Morph's 250 ms and Deno's 200 ms figures measure start time, not CPU speed.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Morph Cloud and Deno Sandbox have no published run in this suite yet, so there is no like-for-like number to compare.

Pricing in five scenarios

Each bill is priced from the providers' public price lists by the open Battleships engine, with the cheapest plan that runs the scenario.

ScenarioMorph Cloud, a monthDeno Sandbox, a monthboat, a month
One coding agent, workdays
4 vCPU / 8 GB, 50 GB disk, 8 hours a day, 22 days a month, files kept between days
$32 · Developer$53 · Pro · with limits$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$121 · Team$200 · Builder · with limits$26 · $20/mo
50 agents in parallel
50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside
$1,459 · Scale$2,779 · Builder · with limits$317 · $20/mo × 3 seats
Sandboxes for your users
2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once
$325 · Scale$783 · Builder · with limits$200 · $100/mo × 2 seats
1,000 short jobs at once
2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month
$869 · Scale$1,563 · Builder · with limits$2,000 · $2000/mo · with limits

Morph Cloud: Morph bills MCUs at $0.05 an hour: a machine uses the largest of its vCPUs, its RAM in 4 GiB steps or its disk in 16 GiB steps. Team ($40 a month) and Scale ($250 a month) are prepaid MCU bundles at a discount, and a paused VM bills only its snapshot.

Deno Sandbox: Sandboxes need Pro at $20 a month or Builder at $200 a month, which include CPU, memory and egress allowances shared with Deno Deploy apps. Past those, CPU costs $0.10 per hour of active CPU time and memory $0.025 per GiB-hour for the whole life of the sandbox.

Deno Sandbox: Plans start at $20 a month, and the whole fee is usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

Morph fits all five scenarios, though disk beyond 16 GiB per MCU raises the bill and egress prices are not published. Deno Sandbox fits none as written: a sandbox lives up to 30 minutes, is fixed at 2 vCPU with up to 4 GB of memory, and Builder allows 20 at once per region. boat fits four of the five; at 1,000 short jobs at once its top plan queues starts, while Morph Scale fits.

ScenarioMorph CloudDeno Sandboxboat
One coding agent, workdays
  • disk beyond 16 GiB: price unknown
  • egress price not published
  • Pro: sessions capped at 0.5 h
  • capped at 2 vCPU / 4 GiB
  • largest size is 2 vCPU / 4 GiB
  • disk beyond 10 GiB: price unknown
None that bite
One agent that never stops
  • disk beyond 16 GiB: price unknown
  • egress price not published
  • Builder: sessions capped at 0.5 h
  • capped at 2 vCPU / 4 GiB
  • largest size is 2 vCPU / 4 GiB
  • disk beyond 10 GiB: price unknown
None that bite
50 agents in parallel
  • disk beyond 16 GiB: price unknown
  • egress price not published
  • Builder: max 20 concurrent
  • Builder: sessions capped at 0.5 h
  • capped at 2 vCPU / 4 GiB
  • largest size is 2 vCPU / 4 GiB
None that bite
Sandboxes for your users
  • egress price not published
  • Builder: max 20 concurrent
None that bite
1,000 short jobs at once
  • egress price not published
  • Builder: max 20 concurrent
  • max 2,400 starts/day (needs ~6,667)
  • max 600 starts/hour (needs ~1,000)
  • bursts above 90 starts/min are queued (a burst of 333 takes ~4 min to start)

Which one should you use?

Use Morph Cloud when

your agents branch from one running state with its memory, sleep between requests and wake on demand, or need experimental Windows and macOS guests.

  • Branch and wake with memory. For agents that fan out from one running state or sleep between requests: a VM keeps its memory, branches and wakes on demand.
  • A full VM that stays up. For agents that work for hours: no lifetime cap, Docker inside, and machine sizes you choose within your account pool.
  • Managed CI runners. For teams that also want GitHub Actions runners, billed from the same MCU balance as their VMs.

Use Deno Sandbox when

you run short pieces of untrusted code that must start in milliseconds, reach only the hosts you allow, or run in the US, especially if you already use Deno Deploy.

  • Locked-down outbound traffic. For untrusted code: each sandbox can be limited to a list of hosts, and real secrets reach only approved hosts.
  • Fast starts, CPU billed while active. For short bursts of code: a sandbox starts in under 200 ms and CPU bills only while code runs.
  • A US region and Deno Deploy. For teams already on Deno Deploy: sandboxes run in Chicago or Amsterdam and can be promoted to Deploy apps.

Where boat fits

If your agents do long, real work, such as coding, building with Docker or using a browser, look at boat as well. It gives a full VM like Morph, with no 30-minute cap, and it comes with the agents, the desktop and the key handling already inside.

Coding agents you drive from outside

On Morph you install the agent and parse its terminal through tmux, and on Deno you run Claude Code through shell commands. boat ships seven agents with a prompt, steer and events API.

Work that is never lost

A Deno sandbox wipes its root disk after at most 30 minutes, and a plain stop on Morph deletes the instance. boat saves the whole disk every minute and on stop, and a stopped sandbox is free.

A desktop, Docker and /dev/kvm

Deno has no desktop and does not document Docker, and Morph's nested virtualization is experimental, with the browser left for you to install. boat has a 60fps desktop with Chromium, Docker and /dev/kvm.

Use boat when your agents do real work for hours: coding agents you steer by API, Docker and /dev/kvm, a desktop with Chromium, real keys kept outside the machine, and a disk that is still there tomorrow. Compare it one to one: boat vs Morph Cloud and boat vs Deno Sandbox.

Questions people ask

Is Morph Cloud cheaper than Deno Sandbox?

In all five scenarios on this page, yes. For example, one agent running all month comes to $121 a month on Morph against $200 on Deno, and Deno does not fit any of the scenarios as written because of its 30-minute lifetime and 2 vCPU size.

Which is faster, Morph Cloud or Deno Sandbox?

Neither has a CPU measurement in the benchmark this page uses. Deno says a sandbox starts in under 200 ms, and Morph says it restores a snapshot in under 250 ms. boat did 26.69 runs per second on that benchmark.

Can Morph Cloud or Deno Sandbox run Docker?

Morph runs Docker, Docker in Docker and local Kubernetes inside its VMs. Deno's docs give root access but do not say Docker works inside a sandbox. boat runs Docker and systemd and exposes /dev/kvm.

How long can each sandbox run?

A Morph VM runs until you stop it or its time to live ends, and it can pause with its memory. A Deno sandbox lives up to 30 minutes. A boat sandbox has no lifetime cap on paid plans.

Can I branch a running sandbox?

Morph can branch a running VM with its memory into many copies in under 250 ms. Deno cannot fork a running sandbox, but many sandboxes can boot from a read-only volume snapshot. boat forks a running sandbox with its disk.

Is boat SOC 2 compliant?

SOC 2 is in progress. We're open about where we stand: live status at status.ascii.dev and our data retention policy at docs.boat.dev/data-retention.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons