CodeSandbox SDK vs Northflank
Both run each sandbox in a microVM with its own kernel. CodeSandbox SDK is built around VMs that hibernate with their memory and wake on the next request, while Northflank is a broad cloud platform with GPUs, regions around the world and your own cloud, where only attached volumes survive a pause.
The companies and products
CodeSandbox SDK
CodeSandbox SDK is an API from CodeSandbox, now a Together AI company, that starts sandboxed development VMs on the same infrastructure as the CodeSandbox editor.
Each sandbox is a Firecracker microVM built from a template or any Dockerfile. When it goes idle it hibernates with a memory snapshot, and it resumes or forks from that snapshot in seconds. You drive it from a TypeScript SDK through terminals, commands, files and HTTPS hosts. Together's docs now call it the legacy offering and point new users to its successor, the together-sandbox SDK.
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. “46th cheapest of 345” means 45 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 workload | CodeSandbox SDK: 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: CodeSandbox SDK keeps its disk, Northflank keeps only attached volumes, and boat keeps the whole disk with SSH and Docker. | 178th of 367, with limits $1,939 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 | 215th of 366, with limits $2,478 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 CodeSandbox SDK is a full match here, since short code runs sleep with their memory and wake on the next request, while Northflank has no idle auto-pause. | 46th cheapest of 345 $642 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 CodeSandbox SDK wakes a user's sandbox on their next HTTP request but caps Scale at 250 at once, while Northflank does not publish its limit; boat places first here. | 140th of 361, with limits $1,707 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 | 348th of 360, with limits $3,861 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 CodeSandbox SDK fits agent evals fully, and its memory forks let many runs start from one warm state; boat fits fully too and places higher. | 64th cheapest of 364 $1,335 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 Both fit CI, and Northflank places well ahead of CodeSandbox SDK; boat adds /dev/kvm for Android and VM builds, which neither documents. | 92nd cheapest of 377 $860 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 box that runs all month suits neither well, since CodeSandbox SDK bills every running minute and Northflank resets everything outside volumes on a pause. | 310th of 368, with limits $240 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 Neither has a desktop, so a computer-use agent needs one built and streamed by you; boat streams a 60fps Linux desktop with Chromium. | 206th of 369, with limits $691 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 | 251st of 367, with limits $443 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 | 281st of 346, with limits $508 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 | 193rd of 338, with limits $7,390 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 | 240th of 360, with limits $326 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 Only Northflank has GPU sandboxes, from L4 to H100 and up; CodeSandbox SDK 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 | CodeSandbox SDK | 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 |
| What survives a stop | Disk and memory: hibernates with a memory snapshot and resumes 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; resume boots the machine again |
| Fork | Fork a hibernated sandbox from its snapshot, or a running one sharing its memory | Filesystem snapshots of a running or stopping sandbox, opt-in; restore into a new one | Fork a running sandbox with its disk |
| Wake on request | Yes; an HTTP request to a host wakes it | No; no idle auto-pause either, a sandbox runs until you pause it | No; a stopped sandbox is started by API |
| Shell access | Terminals, commands and files through the SDK; no SSH | SDK, browser terminal or SSH | SSH, plus exec and files over the API |
| Nested virtualization | Not documented | Not documented inside a sandbox | Yes, /dev/kvm for Android emulators and VMs |
| Desktop and browser | No desktop; a headless Chromium template | Headless; no browser product | 60fps Linux desktop, Chromium and computer use built in |
| Coding agents | Run your own agent through the command API | Harnesses with Claude Code, Codex, Cursor, OpenCode or Pi; you talk to the agent through a terminal or SSH | Seven agents preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Secrets passed in as environment variables | Header injection for listed hosts in the network policy API; otherwise env vars or files | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Inbound access | HTTPS host per port, public by default; no raw TCP or public IP | HTTPS ports, 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 |
| Outbound rules | No egress allowlist | Network policies with allow lists by IP, CIDR or domain | Open internet, no provider-side allowlist |
| GPUs | No | L4, A100, H100, RTX PRO 6000 and more | No |
| Regions | A country hint steers scheduling, but placement is not guaranteed | US, Europe, Asia, Australia, South America and Africa; fixed per project | EU only (Germany, Finland, France) |
| Self-hosting | Not offered | Bring your own cloud, or the control plane in your VPC on Enterprise | No |
Every feature Battleships tracks (43)
| Feature | CodeSandbox SDK | 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 | Not published | Not published | Yes |
| Desktop GUI | No | No | Yes |
| Browser | No | No | Yes |
| Computer-use API | No | No | Yes |
| SSH | No | 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 | No | Yes | No |
| Secret proxy | No | Yes | Yes |
| Secret proxy for any API | No | Yes | Yes |
| Preinstalled agents | No | Yes | Yes |
| Agent harness API | No | No | Yes |
| MCP server | No | No | No |
| GPU | No | Yes | No |
| Windows | No | No | No |
| Arm64 | No | Yes | No |
| Self-hosting | No | Yes | No |
| BYOC | No | Yes | No |
| Open source | No | No | No |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | No | Yes | Yes |
| Audit logs | Not published | Yes | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | No | Yes | No |
| EU data residency | No | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable CPU measurement for CodeSandbox SDK or Northflank: neither has a result on the hpc-sandbox-benchmarks test. 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, so no speed ratio between the three can be given.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. CodeSandbox SDK and Northflank 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.
| Scenario | CodeSandbox SDK, 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 | $193 · Scale | $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 | $341 · Scale | $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 | $2,500 · Scale | $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 | $815 · Scale · with limits | $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 | $1,632 · Scale · with limits | $688 · Developer Sandbox (free tier) · with limits | $2,000 · $2000/mo · with limits |
CodeSandbox SDK: You buy VM credits and each size burns a fixed number per hour, billed per started minute while the VM runs, including the idle time before it hibernates. The Scale plan adds a $170 monthly platform fee that is not usage credit, and a hibernated VM costs nothing.
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
CodeSandbox SDK's Scale plan allows 250 VMs at once, so the user-sandboxes (300) and 1,000-job scenarios do not fit it without Enterprise; each VM has a 20 GB disk, and the price of more disk and of egress is not published. On Northflank the limit that bites is what survives a stop: only attached volumes keep their files, so packages installed anywhere else reset, and how many sandboxes can run at once is not published. boat fits the first four scenarios, but on 1,000 short jobs at once even its $2,000 plan queues starts above 90 a minute.
| Scenario | CodeSandbox SDK | 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 CodeSandbox SDK when
your sandboxes sleep between visits and should wake on the next HTTP request with their memory intact, or when many runs should fork from one warm state, and you are fine building on what Together now calls its legacy SDK.
- Sleeps with its memory. For sandboxes used in short bursts: an idle VM hibernates with its memory and costs nothing until it wakes.
- Wakes on the next request. For previews and user sandboxes: an HTTP request to a host wakes a hibernated VM with its processes still running.
- Forks that share memory. For rollouts and test variants: fork a running or hibernated sandbox and every copy starts from the same live state.
Use Northflank when
you need GPUs next to the agent, regions outside Europe, outbound allow lists, or sandboxes inside your own cloud account next to the rest of your apps.
- GPU sandboxes. For agents that train or run models: Northflank has GPU sandboxes from L4 to H100 and up.
- Regions around the world. For users far from Europe: Northflank runs in the US, Asia, Australia, South America and Africa too.
- Your own cloud, and one platform. For teams that must run in their own AWS, GCP or Azure account, next to their services, jobs and databases.
Where boat fits
If your agents work for hours on one machine, installing tools, running Docker, a browser and servers, look at boat. It is a full VM whose whole disk comes back after every stop, with the agent, a desktop and a credentials proxy already inside, which neither CodeSandbox SDK nor Northflank ships.
A whole machine with /dev/kvm and SSH
Neither CodeSandbox SDK nor Northflank documents nested virtualization, so Android emulators and VM-based tests cannot start. CodeSandbox SDK also has no SSH, so every tool goes through an SDK call. boat has SSH, systemd, Docker and /dev/kvm.
Agents and a desktop you drive from outside
Both are headless, so a computer-use agent needs a desktop you build and stream. On CodeSandbox SDK you bring the agent; Northflank Harnesses start one you reach by terminal or SSH. boat has a 60fps desktop and an API to prompt and steer agents.
The whole disk, saved every minute
A Northflank pause wipes everything outside attached volumes, which bill while paused, so the agent reinstalls its tools. CodeSandbox SDK keeps a 20 GB disk with no published rate for more. boat saves the whole disk every minute and stops are free.
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, with the agent itself driven from your code and its keys kept outside. Compare it one to one: boat vs CodeSandbox SDK and boat vs Northflank.
Questions people ask
Is CodeSandbox SDK cheaper than Northflank?
No. Northflank comes out lower in all five scenarios on this page, for example $108 against $341 a month for one agent that never stops, though on Northflank files outside volumes reset on a pause. boat is $26 a month for the same agent.
Which is faster, CodeSandbox SDK or Northflank?
Neither has a comparable CPU measurement, so there is no fair speed answer. boat did 26.69 runs per second on the hpc-sandbox-benchmarks Node.js loop at 4 vCPU / 8 GB.
Do they keep files when a sandbox stops?
CodeSandbox SDK hibernates with its disk and memory, so processes are still running when it resumes. Northflank keeps only files on attached volumes; the rest of the disk and all processes reset. boat keeps the whole disk on every stop.
Can I run Docker and Android emulators in each?
Both run Docker inside the sandbox. Neither documents nested virtualization, so Android emulators and nested VMs are not covered; boat exposes /dev/kvm for them.
Do CodeSandbox SDK or Northflank have GPUs?
Northflank does, with GPU sandboxes under gVisor from L4 to H100 and more. CodeSandbox SDK has no GPUs, and boat runs on CPUs only.
Is CodeSandbox SDK still maintained?
CodeSandbox is now part of Together AI. Together's docs call the CodeSandbox-based SDK deprecated and name together-sandbox as its successor, while self-serve sign-up still runs through CodeSandbox.
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs CodeSandbox SDK
- boat vs Northflank
- E2B vs CodeSandbox SDK
- Daytona vs CodeSandbox SDK
- Modal vs CodeSandbox SDK
- Vercel Sandbox vs CodeSandbox SDK
- Cloudflare Sandbox vs CodeSandbox SDK
- Blaxel vs CodeSandbox SDK
- Runloop vs CodeSandbox SDK
- Tensorlake vs CodeSandbox SDK
- Morph Cloud vs CodeSandbox SDK
- CodeSandbox SDK vs Fly.io Machines