E2B vs Morph Cloud
Both give each agent its own Linux machine that can pause with its memory and wake on the next request. E2B uses Firecracker microVMs that run up to 24 hours at a time on Pro, with a self-hostable runtime and US, EU and APAC regions. Morph Cloud sells full VMs with no session cap that branch into many copies in under 250 ms.
The companies and products
E2B
E2B calls itself the AI agent cloud: an API that gives each agent session its own isolated Linux machine.
Every E2B sandbox is a Firecracker microVM that boots from a snapshot, so it starts fast and can be paused and resumed with its memory. You build custom sandboxes from templates based on a Docker image, and drive them from Python or JavaScript SDKs. It is built for teams that run many short code, data or agent jobs. Its runtime is open source, and E2B Embed runs it on your own infrastructure.
- Isolation
- Firecracker microVM per sandbox
- Open source and self-hosting
- Runtime under Apache-2.0; E2B Embed runs it with Docker Compose, Terraform or Kubernetes
- Bring your own cloud
- Enterprise data plane in your AWS, GCP or Azure account
- Compliance
- SOC 2 Type II; HIPAA BAA on request
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. It also sells managed GitHub Actions runners and a shared filesystem.
- Regions
- Not published
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. “20th cheapest of 365” means 19 of the other 364 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 workload | E2B: price rank | Morph Cloud: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month All three run Docker and full builds. On Morph you install the coding agent and drive it through tmux; on E2B you run it through the command API. boat installs seven agents with a prompt API. | 20th cheapest of 365 $4,143 a month | 215th of 365, with limits $2,288 a month | 5th cheapest of 365 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB One E2B run stops at 24 hours on Pro; your code pauses and resumes it, and memory survives. Morph runs until you stop it. On boat, turn auto-stop off on a paid plan (default 1 hour). | 82nd of 361, with limits $5,348 a month | 272nd of 361, with limits $3,014 a month | 6th cheapest of 361 $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 that pause with their memory and wake on the next request. Morph bills a paused VM only for its snapshot, and E2B bills nothing while paused. On boat each start counts against the plan's start cap. | 43rd cheapest of 336 $421 a month | 20th cheapest of 336 $154 a month | 189th of 336, 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 E2B and Morph both wake a user's paused machine on the next request. boat gives each user up to 50 token-protected HTTPS URLs, and each start counts against the plan's start cap. | 33rd cheapest of 349 $2,354 a month | 21st cheapest of 349 $905 a month | 3rd cheapest of 349 $209 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month E2B forks a running sandbox with its memory, up to 20 copies per call. Morph branches a running VM with its memory in under 250 ms. Both fit rollouts from one running state. A boat fork copies the disk only. | 5th cheapest of 349 $9,384 a month | 92nd of 349, with limits $4,847 a month | 39th of 349, with limits $2,000 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month | 87th cheapest of 359 $1,975 a month | 51st cheapest of 359 $675 a month | 10th cheapest of 359 $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. Android or VM builds need nested virtualization: boat has /dev/kvm, Morph lists it as experimental, and E2B's docs list it as not supported. | 338th of 374, with limits $1,429 a month | 37th cheapest of 374 $355 a month | 2nd cheapest of 374 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A dev box that runs all month fits Morph and boat with no session cap. On E2B you pause and resume once a day. | 208th of 371, with limits $358 a month | 86th cheapest of 371 $116 a month | 19th cheapest of 371 $26 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month E2B has a Linux desktop for computer use. On Morph you set it up: install the browser and agent on its remote desktop. boat streams a built-in desktop and Chrome at 1920x1080 and 60 fps. | 34th cheapest of 367 $1,342 a month | 219th of 367, with limits $595 a month | 7th cheapest of 367 $200 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month | 126th of 356, with limits $746 a month | 267th of 356, with limits $250 a month | 7th cheapest of 356 $200 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 62nd cheapest of 343 $554 a month | 286th of 343, with limits $234 a month | 6th cheapest of 343 $90 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 226th of 327, with limits $9,223 a month | 152nd of 327, with limits $4,750 a month | 73rd of 327, with limits $1,800 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month | 17th cheapest of 351 $1,043 a month | 245th of 351, with limits $228 a month | 3rd cheapest of 351 $200 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
Key features
| Feature | E2B | Morph Cloud | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel; shared vCPUs | Full VM with its own kernel, with Docker in Docker and local Kubernetes | Full VM with its own kernel, on boat's own AMD Ryzen 7 9700X and Ryzen 9 9950X hosts; shared vCPUs |
| CPU benchmark (V8 Web Tooling, 4 vCPU / 8 GB, StarSling run of 3 October 2026) | 11.08 runs/s, rank 7 of 15 (shared) | Not in the public benchmarks we use | 28.06 runs/s, rank 2 of 15 (shared), on a Ryzen 9 9950X host |
| Session length | One run: up to 1 hour on Hobby, 24 hours on Pro; pausing and resuming resets the clock | No cap; a machine runs until you stop it or its optional time to live ends | No cap once auto-stop is off on a paid plan; auto-stop defaults to 1 hour, up to 30 days |
| Pause with memory and wake on request | Yes; resume takes about 1 second, and a paused sandbox can wake on the next HTTP request or SDK call; $0 while paused | Yes; a paused VM bills only its snapshot and wakes on the next HTTP request, SSH or exec call | No; stop saves the disk, resume is like a reboot, and you start it by API, CLI or dashboard |
| Fork a running machine | With its memory, up to 20 copies per call, with a short pause | With its memory, as many copies as you ask for, in under 250 ms | From its last 1-minute disk snapshot, without memory; writes from the last minute or so can be missing |
| Nested virtualization | Docs list nested-virtualization runtimes as not supported | Experimental | Yes, /dev/kvm on every sandbox for Android emulators and VMs |
| Guest systems | Linux | Linux, with experimental Windows and macOS (x86) | Linux; Windows programs run through Wine on the desktop, no Windows VM |
| Coding agents | Templates and guides for many agents; you run the agent CLI through the command API | You install the agent, then drive it through a tmux API that sends keys and reads the screen | Seven harnesses installed, with a prompt, steer and events API |
| Desktop and computer use | E2B Desktop sandbox with VNC streaming | Browser-based remote desktop; you install the browser and any computer-use agent yourself | Built-in desktop and Chrome at 1920x1080 and 60 fps, with computer tools for agents, embeddable in your app |
| Keeping API keys out of the sandbox | Secrets injected into outbound HTTPS headers, in private beta | No documented key proxy; API keys are set inside the VM | Optional proxy ($1 a day while on, plus $1 per 1,000 requests) for supported model providers and custom HTTPS APIs |
| Inbound access | HTTPS URL per port, public by default unless you turn on a token; no public IP per sandbox | Named HTTP services with optional API key auth; SSH and port forwarding through Morph's gateway; no public raw TCP | Up to 50 HTTPS URLs per sandbox, token-protected by default; raw ports over IPv6 on sandboxes with no IPv4 of their own |
| Outbound rules | Allow and deny lists by IP, CIDR or domain | No provider-side allowlist documented | Open internet; no provider-side allowlist |
| Regions | US by default; EU and APAC enabled by support | Not published | Germany, Finland and France; you cannot pick one; no US or Asia region |
| Self-hosting | Open-source runtime under Apache-2.0 and E2B Embed; bring your own cloud on Enterprise | No; SDKs are open source, the platform is hosted only | No |
Every feature Battleships tracks (43)
| Feature | E2B | Morph Cloud | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No documented way | Yes | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Yes | Yes | Yes |
| Desktop GUI | Yes | Yes | Yes |
| Browser | Yes | No documented way | Yes |
| Computer-use API | Yes | No documented way | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | Yes | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | Yes | Yes |
| Memory fork | Yes | Yes | No documented way |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | Yes | No documented way |
| Wake on request | Yes | Yes | No documented way |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No documented way | No documented way | Yes |
| Public IPv4 | No documented way | No documented way | No documented way |
| Egress allowlist | Yes | No documented way | No documented way |
| Secret proxy | Yes | No documented way | Yes |
| Secret proxy for any API | Yes | No documented way | Yes |
| Preinstalled agents | Yes | No documented way | Yes |
| Agent harness API | No documented way | Yes | Yes |
| MCP server | Yes | No documented way | No documented way |
| GPU | No documented way | No documented way | No documented way |
| Windows | No documented way | Yes | No documented way |
| Arm64 | No documented way | No documented way | No documented way |
| Self-hosting | Yes | No documented way | No documented way |
| BYOC | Yes | No documented way | No documented way |
| Open source | Yes | No documented way | No documented way |
| Scoped API keys | Not published | Yes | Yes |
| Spend limits | Yes | Not published | Yes |
| Usage per sandbox (API) | No documented way | Yes | Yes |
| Audit logs | Not published | Yes | No documented way |
| SSO | No documented way | Not published | No documented way |
| SOC 2 | Yes | Not published | No documented way |
| HIPAA | Yes | Not published | No documented way |
| EU data residency | Yes | Not published | No documented way |
| Zero data retention | Not published | Not published | Yes |
Performance
In StarSling's run of 3 October 2026 (run 37073680030), the V8 Web Tooling Benchmark at 4 vCPU / 8 GB did 28.06 runs/s on boat, second of 15, and 11.08 on E2B, rank 7 (shared). That is about 2.5x. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Providers ran on different hardware in different regions. Morph Cloud is not in the public benchmarks we use, so we cannot say how it compares. Morph says it restores a snapshot in under 250 ms, which measures start time, not CPU speed.
V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Morph Cloud is not in the public benchmarks we use, so we cannot say which is faster.
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. Start limits, per-start fees and plan minimums are in the price, boat's included.
| Scenario | E2B, a month | Morph Cloud, a month | boat, 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 | $202 · Pro | $32 · Developer | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $368 · Pro · with limits | $121 · Team | $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 | $2,773 · Pro | $1,459 · Scale | $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 | $1,395 · Pro+ (600 concurrent) | $325 · Scale | $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 | $2,797 · Pro++ (1,100 concurrent) | $869 · Scale | $8,800 · $2000/mo · with limits |
E2B: E2B bills $0.000014 per vCPU-second and $0.0000045 per GiB-second while a sandbox runs, idle included: $0.33 an hour for 4 vCPU / 8 GiB. A paused sandbox costs nothing. Hobby costs $0 with a one-time $100 credit. Pro costs $150 a month for higher limits, with no usage credit. Pro+ ($650) and Pro++ ($1,150) raise concurrency to 600 and 1,100 sandboxes.
Morph Cloud: Morph bills MCUs at $0.05 each: per hour, a machine uses the largest of its vCPUs, its RAM in 4 GiB steps or its disk in 16 GiB steps. The Free plan costs $0 and includes no MCUs. Team ($40 a month for 1,000 MCUs) and Scale ($250 a month for 7,500 MCUs) are prepaid bundles at a discount. A paused VM bills only its snapshot storage.
Morph Cloud: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. Unused time does not carry over. A 4 vCPU / 8 GB sandbox costs $0.036 an hour, billed per second while it runs, busy or idle. A stopped sandbox has no compute charge, and boat keeps its disk for at least 14 days. Saved snapshots above the included count and the optional AI credentials proxy still charge while sandboxes are stopped. The $20 plan includes 12 starts a minute, 60 an hour and 200 a day; create, fork and resume each count as one start, and an extra start costs $0.03 to $0.07. A card is required, also for the 7-day trial.
Limits in those scenarios
One E2B run stops at 24 hours on Pro, so E2B needs a daily pause for the always-on scenario and is marked as not fitting as-is. E2B Pro includes 20 GiB of disk. Morph prices each machine by its largest resource, so more than 16 GiB of disk per vCPU raises the bill. Neither E2B nor Morph publishes an egress price. Morph's limits are account-wide pools: Free allows up to 64 vCPU, so 16 machines at 4 vCPU. For 1,000 short jobs at once, E2B Pro++ queues bursts above 300 starts a minute and Morph Scale fits. boat's limits: auto-stop defaults to 1 hour, and each plan caps starts. For 1,000 short jobs at once, even the $2,000 plan needs paid extra starts and refuses starts above 270 a minute, so boat does not fit. boat has no US or Asia region.
| Scenario | E2B | Morph Cloud | boat |
|---|---|---|---|
| One coding agent, workdays |
|
| None for this scenario |
| One agent that never stops |
|
| None for this scenario |
| 50 agents in parallel |
|
| None for this scenario |
| Sandboxes for your users |
|
| None for this scenario |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use E2B when
you run many short jobs that pause between requests, need outbound allow lists or US and APAC regions, or want to self-host the runtime.
- Self-hosting and your own cloud. For teams that want to run the sandbox runtime themselves: it is Apache-2.0, E2B Embed runs it on your machines, and Enterprise can run in your AWS, GCP or Azure.
- Outbound allow and deny lists. For agents that should only reach hosts you pick: E2B filters outbound traffic by IP, CIDR or domain.
- Regions in the US, EU and APAC. For teams that must keep machines near US or Asian users: E2B runs in all three. Morph does not publish regions.
Use Morph Cloud when
your agents run for days on full VMs, branch from one running state with its memory, or need managed CI runners and experimental Windows or macOS guests.
- Full VMs with no session cap. For agents that work for days: a Morph VM runs until you stop it, with Docker in Docker and local Kubernetes inside.
- Branching a running state in under 250 ms. For agents that fan out from one point: Morph copies a running VM with its memory into as many branches as you ask for.
- Managed CI runners and other guest systems. For teams that also want GitHub Actions runners from the same balance, or experimental Windows and macOS (x86) guests.
Where boat fits
If your agents do long, real work rather than short bursts, look at boat as well. It gives each agent a full VM with the agents, desktop and optional key proxy already inside. It has no session cap once auto-stop is off on a paid plan (default 1 hour).
Coding agents you drive from outside
boat installs seven coding agents with a prompt, steer and events API. On E2B you run them through the command API, and on Morph you send keystrokes through tmux and parse the screen to know when an agent is done or stuck.
/dev/kvm and more CPU work
E2B's docs list nested virtualization as not supported, and Morph lists it as experimental. boat has /dev/kvm on every sandbox. In StarSling's run of 3 October 2026, boat did 28.06 V8 Web Tooling runs/s and E2B 11.08 at 4 vCPU / 8 GB; Morph is not in that run.
Keys that can stay outside the machine
With boat's optional paid proxy on, the real keys of supported model providers and custom HTTPS APIs stay outside the sandbox; other secrets still enter it. E2B's secret injection is in private beta, and on Morph API keys sit inside a machine the agent controls.
Use boat when your agents do hours of real work: builds, Docker, emulators and a browser on a full VM, with coding agents driven by API and an optional proxy for keys. Turn auto-stop off on a paid plan for long work (default 1 hour). Compare it one to one: boat vs E2B and boat vs Morph Cloud.
boat's own limits
- Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
- Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
- A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
- Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
- boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
- Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
- Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
- Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source
Questions people ask
Is E2B cheaper than Morph Cloud?
No, Morph Cloud costs less in all five scenarios on this page. One coding agent on workdays is $32 a month against $202 on E2B, 50 agents in parallel are $1,459 against $2,773, and 1,000 short jobs at once are $869 against $2,797. boat costs $20 and $317 for the first two, and does not fit the 1,000-job burst because of its start limits.
Which is faster, E2B or Morph Cloud?
Morph is not in the public benchmarks we use, so we cannot say. In StarSling's run of 3 October 2026, E2B did 11.08 V8 Web Tooling runs/s at 4 vCPU / 8 GB, and boat did 28.06 on a Ryzen 9 9950X host. Morph's under-250 ms figure is snapshot restore time, not CPU speed.
Can an E2B or Morph Cloud sandbox run for days?
Yes on both. One E2B run stops after 24 hours on Pro and 1 hour on Hobby; pausing and resuming resets the clock and keeps memory. A Morph VM runs until you stop it or its optional time to live ends. boat has no session cap once auto-stop is off on a paid plan.
Can E2B and Morph Cloud run Docker and Android emulators?
Both run Docker inside the sandbox. E2B's docs list nested virtualization as not supported, and Morph lists it as experimental. boat exposes /dev/kvm for Android emulators and VMs.
Can both fork a running sandbox with its memory?
Yes. E2B forks a running sandbox with its memory, up to 20 copies per call with a short pause, and Morph branches a running VM into as many copies as you ask for in under 250 ms. boat forks a running sandbox from its last 1-minute disk snapshot, so the copy boots fresh.
Can I run Claude Code on E2B or Morph Cloud?
Yes. E2B has templates and guides and runs the agent through its command API. On Morph you install it in a Devbox and drive it through a tmux API. On boat, Claude Code and six other agents come installed, with a prompt, steer and events API.
Try boat
Install the CLI, then run boat new.
7-day free trial