Northflank vs Together Code Sandbox
Northflank is a broad developer platform you can sign up for today, with microVM sandboxes, GPUs, many regions and your own cloud. Together Code Sandbox starts small VMs from Docker-image snapshots and can save their memory, but Together has to enable it for your organization.
The companies and products
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.
Together Code Sandbox
Together AI is a cloud for running and training AI models, and Code Sandbox is its product for running code in isolated VMs.
You build a snapshot from a Docker image or Dockerfile on Together's builder, then start sandboxes from it and run commands and file operations through the together-sandbox SDK or CLI. When a sandbox ends you can save its disk, and its memory too, as a new snapshot to start more sandboxes from. It is aimed at model-generated code, agent tool calls and reinforcement learning rollouts, and it must be enabled for your organization by Together. Together also sells Code Interpreter, a separate API that runs Python code in short sessions.
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. “38th cheapest of 377” means 37 of the other 376 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 | Northflank: price rank | Together Code Sandbox: 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 after a pause, Together documents no Docker inside, and boat keeps the whole disk with Docker and root. | 159th of 367, with limits $1,477 a month | 65th of 367, with limits $528 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB | 173rd of 366, with limits $1,365 a month | 152nd of 366, with limits $1,095 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 For short code runs, Northflank's per-second plans from a tenth of a vCPU fit well, and Together's Code Interpreter runs Python in sessions billed per 60 minutes. | 84th of 345, with limits $115 a month | 326th of 345, with limits $2,190 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 Northflank serves HTTPS ports that are private by default, while on Together every port is public and preview URLs are coming soon; boat adds token-protected HTTPS on up to 50 ports. | 89th of 361, with limits $815 a month | 234th of 361, with limits $900 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 Together can save a sandbox with its memory and start many copies from one warm state; Northflank snapshots files only, and boat forks a running sandbox. | 342nd of 360, with limits $1,762 a month | 315th of 360, with limits $21,900 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 Together documents a Harbor integration for agent evals and Northflank Harnesses start Claude Code or Codex for you; boat ships seven agents with an API to prompt, steer and follow each run. | 134th of 364, with limits $689 a month | 258th of 364, with limits $450 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 runners fully, while Together's self-serve Code Interpreter runs only Python; boat also fits and adds /dev/kvm for emulators, with free stops. | 38th cheapest of 377 $352 a month | 251st of 377, with limits $180 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 151st of 368, with limits $59 a month | 210th of 368, with limits $22 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 Northflank and Together are both headless, so a computer-use agent needs a desktop you build yourself; boat streams a 60fps Linux desktop with Chromium. | 151st of 369, with limits $371 a month | 184th of 369, with limits $600 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 | 200th of 367, with limits $194 a month | 301st of 367, with limits $900 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 | 196th of 346, with limits $117 a month | 219th of 346, with limits $180 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 | 83rd of 338, with limits $2,049 a month | 124th of 338, with limits $3,600 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 | 141st of 360, with limits $99 a month | 167th of 360, with limits $150 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 ranks 4th here with GPU sandboxes from L4 to H100; Together Code Sandbox and boat have no GPU sandboxes. | 4th cheapest of 98 $693 a month | Can't run it | 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 | Northflank | Together Code Sandbox | boat |
|---|---|---|---|
| Isolation | Kata microVM with its own kernel for CPU; gVisor for GPU | A VM per sandbox on Together's infrastructure | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Getting started | Self-serve: free tier with a payment method, then pay as you go | The VM SDK and CLI must be enabled for your organization by Together; only Code Interpreter is self-serve | Sign up and start a sandbox from the API, CLI or dashboard |
| Machine size | Plans from 0.1 vCPU up to 20 vCPU / 40 GB, more on request; a resize restarts the sandbox | 0.1 to 16 cores, 1 to 8 GB of memory per core; disk size fixed | 2 to 16 vCPU with 2 GB per vCPU, up to 16 vCPU / 32 GB on the $100 plan and above |
| What survives a stop | Only attached volumes, which bill while paused; the rest of the disk and all processes reset | End a sandbox with a snapshot of its disk, or disk and memory; a new sandbox resumes with its processes running | The whole disk, saved every minute and on stop; a stopped sandbox costs nothing; resume boots the machine again |
| Snapshots and fork | Opt-in filesystem snapshots of a running sandbox, restored into a new one; no memory snapshots | No live fork: the parent stops, then you start many sandboxes from its snapshot | Automatic disk snapshots; fork a running sandbox while the original keeps running |
| Docker and root | Own kernel per sandbox, so Docker can run inside | Commands run as user 1000 by default, root on request; Docker Compose is not read; Docker inside not documented | Docker, systemd and root on every machine |
| Nested virtualization | Not documented inside a sandbox | Not documented | Yes, /dev/kvm for Android emulators and VMs |
| Reaching the sandbox | SSH and a browser terminal; HTTPS ports on a code.run domain, private by default; public TCP and UDP need a load balancer | SDK and CLI only, no SSH; all ports public; preview URLs coming soon | SSH; HTTPS URLs for up to 50 ports, token-protected by default; raw TCP on a dedicated IPv6 or IPv4 |
| Desktop and browser | Headless; access by SDK, browser terminal or SSH | None; headless command and file access only | 60fps Linux desktop, Chromium and computer use built in |
| Coding agents | Harnesses with Claude Code, Codex, Cursor, OpenCode or Pi; you talk to the agent through a terminal or SSH | Run your own agent through execs; a Harbor guide for agent evals | Seven agents preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Header injection for listed hosts in the network policy API | No credentials proxy documented | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| GPUs | GPU sandboxes with L4, A100, H100, RTX PRO 6000 and more | No GPU sandboxes; GPU clusters are a separate Together product | No |
| Regions and your own cloud | US, Europe, Asia, Australia, South America and Africa; bring your own cloud | Regions not published; no self-hosting | EU only (Germany, Finland, France) |
| Hosted code interpreter | No separate product | Code Interpreter API runs Python in sessions billed per 60 minutes | No separate product; run code through exec in a sandbox |
Every feature Battleships tracks (43)
| Feature | Northflank | Together Code Sandbox | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Not published | Yes |
| Nested virtualization | No | No | Yes |
| Root | Not published | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | No | Yes |
| Browser | No | No | Yes |
| Computer-use API | No | No | Yes |
| SSH | Yes | No | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | No | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | No | Yes |
| Memory fork | No | Yes | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | No | No | No |
| Wake on request | No | No | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | Yes | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | No | No |
| Secret proxy | Yes | No | Yes |
| Secret proxy for any API | Yes | No | Yes |
| Preinstalled agents | Yes | No | Yes |
| Agent harness API | No | No | Yes |
| MCP server | No | Yes | No |
| GPU | Yes | No | No |
| Windows | No | No | No |
| Arm64 | Yes | No | No |
| Self-hosting | Yes | No | No |
| BYOC | Yes | No | No |
| Open source | No | No | No |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Not published | Yes | Yes |
| Usage per sandbox (API) | Yes | Yes | Yes |
| Audit logs | Yes | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Yes | No | No |
| EU data residency | Yes | Not published | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable CPU measurement for Northflank Sandboxes or Together Code Sandbox: 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.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Northflank and Together Code 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.
| Scenario | Northflank, a month | Together Code Sandbox, 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 | $32 · Developer Sandbox (free tier) · with limits | $5 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $108 · Developer Sandbox (free tier) · with limits | $22 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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 | $1,322 · Developer Sandbox (free tier) · with limits | $264 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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 | $361 · Developer Sandbox (free tier) · with limits | $900 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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 | $688 · Developer Sandbox (free tier) · with limits | $6,000 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | $2,000 · $2000/mo · with limits |
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.
Together Code Sandbox: Together lists Code Sandbox at $0.0446 per vCPU-hour and $0.0149 per GiB-hour, but the VMs must be enabled for your organization, so the table prices Code Interpreter: $0.03 per 60-minute session from prepaid credits, with a $5 minimum.
Together Code 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 whole disk.
Limits in those scenarios
Neither Northflank nor Together fits these scenarios as priced. On Northflank only attached volumes survive a stop, so packages installed elsewhere reset, and how many sandboxes can run at once is not published, so 300 or 1,000 at a time is not confirmed. The Together column is Code Interpreter: sessions last 60 minutes, nothing is kept, it runs only Python and its machine size is not published. boat's limit is in the burst scenario, where starts above 90 a minute are queued.
| Scenario | Northflank | Together Code Sandbox | 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 Northflank when
you need GPUs next to the agent, regions outside Europe, sandboxes in your own cloud account, or one self-serve platform for apps and sandboxes.
- GPU sandboxes. For agents that train or run models: Northflank has GPU sandboxes from L4 to H100 and up, billed per hour.
- Regions and your own cloud. For users far from Europe or teams that must stay in their own AWS, GCP or Azure account.
- One self-serve platform. For teams that want sandboxes, services, jobs and databases on one platform they can sign up for today.
Use Together Code Sandbox when
you already run models on Together and want light sandboxes you can save with their memory and branch from, or a simple Python runner billed per session.
- Memory snapshots to branch from. For rollouts and test variants: save a sandbox with its memory and start many copies with processes still running.
- Sandboxes next to your models. For teams already running inference or fine-tuning on Together: sandboxes and models share one account and API key.
- Tiny machines and a Python runner. For many light jobs: sandboxes start at a tenth of a core, and a Python interpreter API bills per session.
Where boat fits
If your agents work on one machine for hours or days, look at boat. It keeps the whole disk on every stop, runs Docker and /dev/kvm, ships a desktop and coding agents you drive from your code, and you can start it today.
The whole machine comes back
A Northflank pause wipes everything outside attached volumes, which bill while paused. Together keeps state only if you end the sandbox with a snapshot. boat saves the whole disk every minute and on stop, and stops are free.
Docker, KVM and a desktop inside
Neither documents /dev/kvm, Together does not document Docker inside, and both are headless, so emulators fail and a computer-use agent needs a desktop you build and stream. boat has all of it in every sandbox.
Agents driven from outside, keys kept out
Northflank Harnesses reach the agent through a terminal or SSH, and on Together you wire every step through execs with keys inside the machine. boat has a prompt, steer and events API 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, with Docker, emulators, a desktop and the agent itself driven from your code. Compare it one to one: boat vs Northflank and boat vs Together Code Sandbox.
Questions people ask
Is Northflank cheaper than Together Code Sandbox?
Together's only self-serve price is Code Interpreter, which does not fit these scenarios. It looks lower for small runs, $22 against $108 a month for one agent that never stops, but costs more at scale: $900 against $361 for sandboxes for your users, and $6,000 against $688 for 1,000 short jobs at once.
Which is faster, Northflank or Together Code Sandbox?
Neither has a comparable CPU measurement, so there is no fair speed ratio between them. boat did 26.69 runs per second on the hpc-sandbox-benchmarks Node.js test at 4 vCPU / 8 GB.
Can Northflank or Together Code Sandbox run Docker?
Northflank gives each CPU sandbox its own kernel, so Docker can run inside. Together's new SDK runs commands as user 1000 by default, does not read Docker Compose and does not document Docker inside. boat runs Docker, systemd and root on every machine and exposes /dev/kvm.
Can I sign up for Together Code Sandbox today?
The VM SDK and CLI must be enabled for your organization, so you ask Together for access. Code Interpreter is self-serve from prepaid credits. Northflank and boat both let you sign up and start a sandbox yourself.
Which one has GPUs?
Northflank has GPU sandboxes under gVisor with cards from L4 to H100 and more. Together sells GPU clusters, but Code Sandbox itself has no GPU. boat runs on CPUs only.
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