CodeSandbox SDK vs Docker Cloud Sandboxes
Both start a small VM per sandbox that can pause with its memory. CodeSandbox SDK is an API for sandboxes that sleep and wake on the next HTTP request, while Docker Cloud Sandboxes moves the sbx coding-agent microVMs from your laptop to the cloud, for up to 24 hours each.
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.
Docker Cloud Sandboxes
Docker Cloud Sandboxes runs Docker's sbx coding-agent microVMs on Docker-managed compute instead of your laptop.
Each sandbox is a microVM with its own Linux kernel and its own Docker Engine, started from the same sbx CLI you use locally, with Claude Code, Codex and other agents ready to run. You can move a sandbox from your laptop to the cloud and back, publish HTTPS ports and SSH in. It launched on September 24, 2026, is billed pay-as-you-go on a personal Docker account, and is built for developers who want their local agent sandboxes to keep going off their machine.
- Launched
- September 24, 2026
- Session length
- 1 hour by default, extendable to 24 hours from creation
- Default quota
- 10 concurrent and 50 stored sandboxes per account
- 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. “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 | Docker Cloud Sandboxes: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory runs agents for days; Docker ends each sandbox at 24 hours, and neither offers SSH plus /dev/kvm the way boat does. | 178th of 367, with limits $1,939 a month | 280th of 367, with limits $4,928 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 can run on CodeSandbox SDK, but not in one Docker session, which ends after 24 hours. | 215th of 366, with limits $2,478 a month | 276th of 366, with limits $5,110 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 fits short code runs best of the three here, with VMs that hibernate with their memory and wake on the next request. | 46th cheapest of 345 $642 a month | 119th of 345, with limits $233 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 Neither fits 300 users at once: CodeSandbox SDK's Scale plan stops at 250 VMs and Docker at 10 by default, while boat fits it. | 140th of 361, with limits $1,707 a month | 136th of 361, with limits $1,628 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 Both can fork a running sandbox with its memory, which suits rollouts branching from one warm state. | 348th of 360, with limits $3,861 a month | 114th of 360, with limits $7,000 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 | 64th cheapest of 364 $1,335 a month | 167th of 364, with limits $1,400 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 CodeSandbox SDK allows far more VMs at once than Docker's default of 10, but neither documents /dev/kvm for Android or VM builds, which boat has. | 92nd cheapest of 377 $860 a month | 172nd of 377, with limits $672 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Docker fits a monthly dev box better than CodeSandbox SDK, but its sessions still end at 24 hours; boat has no session cap. | 310th of 368, with limits $240 a month | 127th of 368, with limits $204 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 Computer-use agents need a screen; neither CodeSandbox SDK nor Docker has a desktop, while boat streams one at 60fps with Chromium. | 206th of 369, with limits $691 a month | 268th of 369, with limits $1,400 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 | 277th of 367, with limits $700 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 | 262nd of 346, with limits $350 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 | 190th of 338, with limits $7,000 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 | 248th of 360, with limits $350 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 it | 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 | CodeSandbox SDK | Docker Cloud Sandboxes | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | MicroVM with its own Linux kernel and its own Docker Engine; hypervisor not named | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Session length | No hard cap; hibernates after an idle timeout of up to one day | 1 hour by default, at most 24 hours from creation | No cap on paid plans; you set the time to live |
| Sandboxes at once | 10 on Build, 250 on Scale, more on Enterprise | 10 by default; no published way to raise it | 100 on the $20 plan, up to 2,000 on higher plans, self-serve |
| Biggest machine | 16 cores / 32 GB on Scale, 64 cores / 128 GB on Enterprise | 16 vCPU / 32 GiB | 16 vCPU / 32 GB on the $100 plan and above |
| Pause and resume | Hibernates with a memory snapshot; resumes with processes still running | Stop keeps memory and files; resume picks up where it left off | 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 | Snapshot a running sandbox with disk or disk and memory, then restore it as a new sandbox | Fork a running sandbox with its disk |
| Wake on request | Yes; an HTTP request to a host wakes the sandbox | Not documented | No; a stopped sandbox is started by API |
| Docker and nested virtualization | Docker and root; /dev/kvm not documented | Its own Docker Engine, agent as non-root with sudo; /dev/kvm not documented | Docker, systemd, root and /dev/kvm for Android emulators and VMs |
| Shell access | Terminals, commands and files through the SDK; no SSH | SSH with Docker-issued certificates, plus the sbx CLI | SSH, plus exec and files over the API |
| Inbound access | HTTPS host per port, public by default, signed tokens for private hosts; no raw TCP | Public HTTPS URL per published port, not protected by Docker sign-in; not a TCP tunnel | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6 |
| Desktop and browser | No desktop; a headless Chromium template | Terminal sessions only | 60fps Linux desktop with Chromium and computer use |
| Coding agents | Run your own agent through the command API | Claude Code, Codex, Copilot, OpenCode and more, run and attached to from the sbx CLI | Seven agents preinstalled, with a prompt, steer and events API to drive them from outside |
| Keeping API keys out of the sandbox | Secrets passed in as environment variables | Cloud proxy sets the auth header for AI services and custom hosts; the sandbox sees a placeholder | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Outbound rules | No allowlist documented | Allow and deny rules by host, with allow-all, balanced and deny-all presets | Open internet, no provider-side allowlist |
Every feature Battleships tracks (43)
| Feature | CodeSandbox SDK | Docker Cloud Sandboxes | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | 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 | Yes | 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 | Not published | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | Not published | 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 | Yes | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | No | Yes | No |
| Self-hosting | No | No | No |
| BYOC | No | No | 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 | No | Yes |
| Audit logs | Not published | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | No | No |
| HIPAA | No | No | No |
| EU data residency | No | No | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable CPU measurement for CodeSandbox SDK or Docker Cloud Sandboxes: neither is in the hpc-sandbox-benchmarks runs, and Docker does not say what hardware it uses. boat did 26.69 runs per second on that Node.js benchmark 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. CodeSandbox SDK and Docker Cloud Sandboxes 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 | Docker Cloud Sandboxes, 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 | $49 · Docker Agentic Platform (pay-as-you-go) | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $341 · Scale | $204 · Docker Agentic Platform (pay-as-you-go) · 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 | $2,464 · Docker Agentic Platform (pay-as-you-go) · 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 | $700 · Docker Agentic Platform (pay-as-you-go) · 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 | $1,400 · Docker Agentic Platform (pay-as-you-go) · 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. Larger teams pay a $170 monthly Scale platform fee on top, and a hibernated VM costs nothing.
Docker Cloud Sandboxes: Docker bills per second for the size you pick, from $0.07 an hour for 1 vCPU / 2 GiB to $1.12 an hour for 16 vCPU / 32 GiB, with no monthly fee. A stopped sandbox costs nothing, and volumes and egress are free.
Docker Cloud Sandboxes: 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
Docker ends every sandbox 24 hours after creation, so one agent that never stops does not fit it, and its default of 10 sandboxes at once rules it out for 50 agents in parallel. CodeSandbox SDK fits both, but its Scale plan caps at 250 VMs, so neither fits 300 user sandboxes or 1,000 short jobs at once. CodeSandbox SDK gives each VM a 20 GB disk and does not publish the price of more disk or of egress. boat fits all but the 1,000-job burst, where even the $2,000 plan queues starts.
| Scenario | CodeSandbox SDK | Docker Cloud Sandboxes | boat |
|---|---|---|---|
| One coding agent, workdays |
| None that bite | 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
you run previews or code runs that sleep between visits and should wake on the next HTTP request with their memory intact, and you are fine building on what Together now calls its legacy SDK.
- Wake on the next request. For previews and code runs used in bursts: a hibernated VM wakes on an HTTP request with its processes still running.
- No 24-hour cap and more at once. A busy sandbox can run past a day, and the Scale plan runs 250 VMs at once instead of 10.
- Bigger machines on Enterprise. Teams that need very large single machines can get up to 64 cores and 128 GB through Enterprise sales.
Use Docker Cloud Sandboxes when
you already run agents in sbx on your laptop and want a few of them to keep going in the cloud for up to a day, with strict outbound rules.
- Coding agents ready to run. Claude Code, Codex and other agents start from the sbx CLI, with SSH and a proxy that keeps API keys out.
- Outbound rules at the proxy. Teams that must limit where an agent connects can set allow and deny rules by host, enforced outside the VM.
- The same sandbox on your laptop. If you already run sbx locally, the cloud is the same microVM and CLI, and you can move a sandbox either way.
Where boat fits
Both of these give an agent a small VM with Docker inside, but neither has a screen, /dev/kvm or raw TCP. If your agents work for days, test mobile apps, use a browser or run servers other people reach, boat gives each one a full machine with the agent already set up.
A whole machine, screen included
Neither documents /dev/kvm, so Android emulators and nested VMs cannot start, and neither has a desktop. boat has both, with a 60fps desktop and Chromium; on the other two you add a separate browser service.
Runs as long and as wide as the work
Docker ends a sandbox 24 hours after creation and runs 10 at a time, and CodeSandbox SDK's Scale plan stops at 250. boat has no session cap on paid plans and runs up to 2,000 at once, self-serve.
Drive agents inside from outside
CodeSandbox SDK has no agents, and Docker's are reached by attaching to a terminal, so you parse text to know when work is done. boat's preinstalled agents take prompts and send structured events through one API.
Use boat when your agents run for days or by the dozen, need Android emulators, a desktop or a browser, or have to be driven from your own app through an API. Compare it one to one: boat vs CodeSandbox SDK and boat vs Docker Cloud Sandboxes.
Questions people ask
Is CodeSandbox SDK cheaper than Docker Cloud Sandboxes?
For one coding agent on workdays, Docker is cheaper: $49 a month against $193 on CodeSandbox SDK's Scale plan, and $20 on boat. For one agent that never stops or 50 agents at once, CodeSandbox SDK fits and Docker does not, because of its 24-hour cap and its default of 10 sandboxes.
Which is faster, CodeSandbox SDK or Docker Cloud Sandboxes?
Neither has a comparable CPU measurement, so there is no fair speed comparison. boat did 26.69 runs per second on the hpc-sandbox-benchmarks Node.js test at 4 vCPU / 8 GB.
Can both run Docker inside?
Yes. CodeSandbox SDK builds sandboxes from any Dockerfile and runs Docker with root, and each Docker cloud sandbox has its own Docker Engine. Neither documents /dev/kvm for Android emulators, which boat exposes.
Can a sandbox run longer than 24 hours?
On CodeSandbox SDK, yes: there is no hard cap, only an idle timeout of up to one day before it hibernates. A Docker cloud sandbox ends 24 hours after creation at most. boat has no session cap on paid plans.
Can I SSH into them?
Docker cloud sandboxes take SSH with Docker-issued certificates. CodeSandbox SDK connects through its SDK, Node and browser clients, with terminals and commands but no SSH. Every boat sandbox has SSH.
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 Docker Cloud Sandboxes
- 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 Northflank