E2B vs Northflank
Both give each agent a microVM with its own kernel. E2B is built for short jobs that pause with their memory and wake on the next request, while Northflank is a broad cloud platform with GPUs, many regions and no session cap, where only attached volumes survive a pause.
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, and its runtime is open source.
- Isolation
- Firecracker microVM per sandbox
- Bring your own cloud
- Enterprise data plane in your AWS, GCP or Azure account
- Compliance
- SOC 2 Type II; HIPAA BAA on request
- Machine size
- 1 to 8 vCPU and 1 to 8 GiB RAM, CPU only
Northflank
Northflank is a London developer platform for running services, jobs and databases on Kubernetes, and Sandboxes is its product for running untrusted code.
A Northflank sandbox is a container image deployed as a service: CPU sandboxes run in Kata microVMs with their own kernel, and GPU sandboxes run under gVisor. You create and drive them from the JavaScript or Python SDK, the CLI or the dashboard, on Northflank's cloud or inside your own. It suits teams that already want one platform for apps, databases, GPUs and sandboxes.
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 367” means 15 of the other 366 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 | Northflank: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A coding agent installs packages all over the machine; Northflank keeps only attached volumes across a pause and E2B stops at 24 hours, while boat keeps the whole disk with no cap. | 16th cheapest of 367 $4,143 a month | 159th of 367, with limits $1,477 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 hits E2B's 24-hour cap, and on Northflank its installed tools reset on every pause; boat keeps running and keeps its whole disk. | 51st of 366, with limits $5,348 a month | 173rd of 366, with limits $1,365 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 E2B is built for short code runs that pause with their memory and wake on the next request; Northflank's small per-second plans cost less but do not wake on request. | 37th cheapest of 345 $421 a month | 84th of 345, with limits $115 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 | 23rd cheapest of 361 $2,354 a month | 89th of 361, with limits $815 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 E2B ranks 2nd here: memory forks and a high start rate suit many short rollouts that branch from the same state, which Northflank does not offer. | 2nd cheapest of 360 $9,384 a month | 342nd of 360, with limits $1,762 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 | 78th cheapest of 364 $1,975 a month | 134th of 364, with limits $689 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 Northflank fits CI better than E2B, with no session cap and small per-second plans; boat adds /dev/kvm for Android emulators and VM builds, and its stops are free. | 337th of 377, with limits $1,429 a month | 38th cheapest of 377 $352 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 runs all month needs no session cap and a disk that stays put, which boat has, while E2B caps sessions and Northflank resets everything outside volumes. | 192nd of 368, with limits $358 a month | 151st of 368, with limits $59 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 E2B has a Linux desktop for computer use, while Northflank sandboxes are headless; boat streams its desktop at 60fps and can be embedded in your app. | 32nd cheapest of 369 $1,342 a month | 151st of 369, with limits $371 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 | 100th of 367, with limits $746 a month | 200th of 367, with limits $194 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 | 57th cheapest of 346 $554 a month | 196th of 346, with limits $117 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 | 227th of 338, with limits $9,223 a month | 83rd of 338, with limits $2,049 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 | 11th cheapest of 360 $1,043 a month | 141st of 360, with limits $99 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 Northflank has GPU sandboxes from L4 to H100 and up; E2B and boat are CPU only. | Can't run it | 4th cheapest of 98 $693 a month | Can't run it |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Can't run it | Can't run it | Can't run it |
Key features
| Feature | E2B | Northflank | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | Kata microVM with its own kernel for CPU; gVisor for GPU | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| CPU benchmark (4 vCPU / 8 GB) | 12.61 runs/s | No comparable measurement | 26.69 runs/s |
| Session length | Up to 1 hour on Hobby, 24 hours on Pro; pausing resets the clock | No documented cap; runs until you pause or delete it | No cap on paid plans; you set the time to live |
| What survives a pause or stop | Memory and disk; resume takes about 1 second with processes still running | Only attached volumes, which bill while paused; the rest of the disk and all processes reset | The whole disk, saved every minute and on stop; stopped sandboxes cost nothing |
| Fork | Fork a running sandbox with its memory, up to 20 copies per call | Filesystem snapshots of a running sandbox, opt-in; restore into a new one | Fork a running sandbox with its disk |
| Wake on request | Yes; a paused sandbox resumes on the next HTTP request or SDK call | No; no idle auto-pause either, so a sandbox bills until you pause it | No; a stopped sandbox is started by API |
| Nested virtualization | Not supported | Not documented inside a sandbox | Yes, /dev/kvm for Android emulators and VMs |
| Desktop and browser | Linux desktop for computer use | Headless; access by SDK, browser terminal or SSH | 60fps Linux desktop, Chromium and computer use built in, embeddable in your app |
| Coding agents | Templates and guides for many agents, run through the command API | Harnesses with Claude Code, Codex, Cursor, OpenCode or Pi, reached through a terminal or SSH | Seven agents preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Secrets injected into outbound HTTPS headers (private beta) | Header injection for listed hosts in the network policy API | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Inbound access | HTTPS URL per port, public by default unless you turn on a token; no dedicated IP | HTTPS ports on a code.run domain, private by default; public TCP and UDP need a separate load balancer | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6 |
| Biggest machine | Up to 8 vCPU / 8 GiB self-serve, more on request | Up to 20 vCPU / 40 GB, more on request; a resize restarts the sandbox | Up to 16 vCPU / 32 GB on the $100 plan and above |
| GPUs | No, CPU only | L4, A100, H100, RTX PRO 6000 and more | No |
| Regions and self-hosting | US, EU and APAC; open-source runtime and bring your own cloud on Enterprise | US, Europe, Asia, Australia, South America and Africa; your own cloud, or the control plane in your VPC on Enterprise | EU only (Germany, Finland, France); no self-hosting |
Every feature Battleships tracks (43)
| Feature | E2B | Northflank | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Not published | Yes |
| Systemd | Yes | Not published | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | Yes | No | Yes |
| Computer-use API | Yes | No | 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 | No | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | No | No |
| Wake on request | Yes | No | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | Yes | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Yes | No |
| Secret proxy | Yes | Yes | Yes |
| Secret proxy for any API | Yes | Yes | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | No | No | Yes |
| MCP server | Yes | No | No |
| GPU | No | Yes | No |
| Windows | No | No | No |
| Arm64 | No | Yes | No |
| Self-hosting | Yes | Yes | No |
| BYOC | Yes | Yes | No |
| Open source | Yes | No | No |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Yes | Not published | Yes |
| Usage per sandbox (API) | No | Yes | Yes |
| Audit logs | Not published | Yes | No |
| SSO | No | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Yes | Yes | No |
| EU data residency | Yes | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
E2B and boat were measured in the same StarSling hpc-sandbox-benchmarks run, on a Node.js build-and-test loop at 4 vCPU / 8 GB: boat did 26.69 runs per second and E2B did 12.61, about twice as much CPU work for boat. Northflank Sandboxes has no result on that benchmark, so there is no comparable CPU number for it.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Northflank has 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.
| Scenario | E2B, a month | Northflank, 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 Sandbox (free tier) · with limits | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $368 · Pro · with limits | $108 · Developer Sandbox (free tier) · 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 | $2,773 · Pro | $1,322 · Developer Sandbox (free tier) · 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 | $1,395 · Pro+ (600 concurrent) | $361 · Developer Sandbox (free tier) · 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 | $2,797 · Pro++ (1,100 concurrent) | $688 · Developer Sandbox (free tier) · with limits | $2,000 · $2000/mo · with limits |
E2B: E2B bills per second for the vCPU and RAM you set, idle time included, until you pause or kill the sandbox. Pro costs $150 a month for higher limits, with no usage credit, and more concurrency costs $500 a month per 500 slots.
Northflank: Northflank bills per second for the plan size you pick, with no monthly fee, until you pause the sandbox; there is no idle auto-pause. Volumes cost $0.15 per GB a month even while paused, and outbound traffic costs $0.06 per GB.
Northflank: 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 whole disk.
Limits in those scenarios
On raw price Northflank comes in under E2B in every scenario, but it does not fully fit any of them: only attached volumes keep their files across a stop, and it does not publish how many sandboxes can run at once, so 300 or 1,000 at a time is not confirmed. E2B caps a session at 24 hours on Pro, which is why it misses the always-on scenario, and its Pro plan includes 20 GiB of disk. For 1,000 short jobs at once, E2B Pro++ fits and only queues bursts above 300 starts a minute, while boat's $2,000 plan caps starts per hour and per day.
| Scenario | E2B | Northflank | boat |
|---|---|---|---|
| One coding agent, workdays |
|
| None that bite |
| One agent that never stops |
|
| None that bite |
| 50 agents in parallel |
|
| None that bite |
| Sandboxes for your users |
|
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use E2B when
you run many short jobs that pause between requests, wake on the next call, or fork from one memory state.
- Memory pause and wake on request. For short jobs that sleep between requests: a paused E2B sandbox comes back in about a second with its processes running.
- Memory forks for branching work. For RL rollouts and evals that branch from one state: E2B forks a running sandbox with its memory, up to 20 copies per call.
- Open-source runtime and a desktop. For teams that want to read or run the runtime themselves, or need a Linux desktop for computer-use agents.
Use Northflank when
you need GPUs next to the agent, regions outside Europe and the US, or sandboxes inside your own cloud next to the rest of your apps.
- GPU sandboxes. For agents that train, fine-tune or run models: Northflank has GPU sandboxes from L4 to H100 and up.
- No session cap and bigger machines. For work that runs for days on one machine: no documented session cap, and plans up to 20 vCPU / 40 GB.
- Regions, your own cloud and one platform. For teams with users far from Europe, or that want sandboxes in their own cloud next to their apps and databases.
Where boat fits
If your agents do long work on one machine, installing packages, running Docker and builds, then coming back the next day, both E2B and Northflank make you work around something: E2B's 24-hour cap, or Northflank wiping everything outside volumes on a pause. boat gives each agent a full VM that keeps its whole disk, has no session cap on paid plans, and ships the agent, desktop and browser inside.
The whole machine comes back, for as long as you need
E2B stops a session at 24 hours on Pro, so your code must pause and resume it. Northflank has no cap, but a pause resets everything outside attached volumes, which bill while paused. boat saves the whole disk every minute, and stops are free.
Faster CPUs and /dev/kvm
boat did 26.69 runs per second on the CPU benchmark against 12.61 for E2B, so builds and tests finish sooner. Neither E2B nor Northflank offers nested virtualization, so Android emulators and VMs cannot start there.
Agents, desktop and keys built in
Northflank Harnesses are reached through a terminal or SSH, and E2B runs agents through its command API, so you build the control layer. boat preinstalls seven agents with a prompt and steer API, a 60fps desktop, and a credentials proxy for any HTTPS API.
Use boat when your agents work on one machine for hours or days and should find it as they left it: installs, Docker, emulators, a desktop and a browser, on a fast machine with the agent driven from your code. Compare it one to one: boat vs E2B and boat vs Northflank.
Questions people ask
Is E2B cheaper than Northflank?
No, on raw price Northflank costs less in all five scenarios: one agent that never stops is $108 a month on Northflank against $368 on E2B. But Northflank resets everything outside attached volumes on a pause, so a fair setup adds volumes, and boat is $26 a month for the same agent.
Which is faster, E2B or Northflank?
E2B did 12.61 runs per second on the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB, and Northflank has no result on that test, so there is no fair CPU comparison. boat did 26.69 runs per second in the same run as E2B.
Can an E2B or Northflank sandbox run for days?
E2B stops a session after 24 hours on Pro and 1 hour on Hobby, though pausing and resuming resets the clock. Northflank documents no cap, and a sandbox runs until you pause or delete it. boat has no session cap on paid plans.
What happens to my files when I pause?
E2B saves memory and disk, and resumes in about a second with processes still running. Northflank keeps only attached volumes; the rest of the disk and all processes reset. boat saves the whole disk every minute and on stop, and resuming boots the machine again.
Can E2B or Northflank run Docker and Android emulators?
Both give each sandbox its own kernel, so Docker can run inside. E2B's docs say nested virtualization is not supported and Northflank does not document it, so Android emulators and VMs are out. boat exposes /dev/kvm for both.
Do E2B or Northflank have GPUs?
Northflank does, with GPU sandboxes under gVisor from L4 to H100 and more. E2B is CPU only, and so is boat.
Try boat
Install the CLI, then run boat new.
7-day free trial