CodeSandbox SDK vs Upstash Box
CodeSandbox SDK gives each sandbox a Firecracker microVM that runs Docker and hibernates with its memory, so it wakes with its processes still running. Upstash Box gives each agent a light container with a coding agent built in, billed only for the CPU it uses, but with no Docker inside.
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.
Upstash Box
Upstash Box is a cloud computer for AI agents from Upstash, the company known for serverless Redis, Vector and QStash.
Each box is a Docker container with its own filesystem, shell, git and an optional coding agent such as Claude Code, Codex or OpenCode, which you drive from TypeScript or Python SDKs. A box pauses when it sits idle, keeps its files, and you pay for the CPU it actually uses. Upstash built it to run its own Context7 service and opened it to everyone in March 2026.
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 | Upstash Box: 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 needs Docker for databases and test services, which CodeSandbox SDK runs and an Upstash box, itself a container, does not; boat adds SSH, /dev/kvm and built-in agents. | 178th of 367, with limits $1,939 a month | 61st of 367, with limits $464 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 | 103rd of 366, with limits $475 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 Both suit short code runs: Upstash bills only the CPU a box uses, and CodeSandbox SDK hibernates with its memory and wakes on the next request. | 46th cheapest of 345 $642 a month | 10th cheapest of 345 $119 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 Upstash fits up to 300 users at once, while CodeSandbox SDK's Scale plan stops at 250 VMs; boat fits too and adds raw TCP, SSH and a desktop. | 140th of 361, with limits $1,707 a month | 2nd cheapest of 361 $222 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 CodeSandbox SDK's memory forks let many rollouts branch from the same running state, which Upstash's file snapshots do not. | 348th of 360, with limits $3,861 a month | 352nd of 360, with limits $8,068 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 Both fit eval runs; CodeSandbox SDK can fork many runs from one warm memory state, and Upstash can start many boxes from one snapshot. | 64th cheapest of 364 $1,335 a month | 52nd cheapest of 364 $1,011 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 runs Docker builds inside its VMs, which an Upstash container cannot; boat also has /dev/kvm for Android builds. | 92nd cheapest of 377 $860 a month | 120th cheapest of 377 $1,520 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A flat-price keep-alive Upstash box makes a light dev box that stays on, while CodeSandbox SDK bills every running minute; boat's is a full VM with a bigger disk. | 310th of 368, with limits $240 a month | 10th cheapest of 368 $20 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: both offer only a headless Chromium, while boat streams a full Linux desktop at 60fps with computer-use tools. | 206th of 369, with limits $691 a month | 73rd of 369, with limits $76 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 | 49th of 367, with limits $38 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 | 37th cheapest of 346 $400 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 | 200th of 338, with limits $8,000 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 | 225th of 360, with limits $259 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 | Upstash Box | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | Docker container per box on AWS | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Docker inside | Yes, with root; built from any Dockerfile | Not documented; the box is itself a container, and custom images are listed as coming soon | Yes, Docker and systemd run as on any Linux server |
| Nested virtualization | Not documented | No; boxes are containers | Yes, /dev/kvm for Android emulators and VMs |
| Biggest machine | 16 cores / 32 GB on Scale, up to 64 cores / 128 GB on Enterprise | Large: 8 vCPU / 16 GB | Up to 16 vCPU / 32 GB on the $100 plan and above |
| Disk | 20 GB per VM; price for more is not published | 5, 10 or 20 GB by size, billed per GB-month | 50 GB at the default 4 vCPU / 8 GB size, 12 to 251 GB by size |
| Pause and resume | Hibernates with a memory snapshot; resumes with processes still running | Pauses when idle and keeps its files; storage keeps billing while paused | Disk saved every minute and on stop; a stopped sandbox costs nothing, and resume boots again |
| Wake on request | Yes; an HTTP request to a host wakes it | Yes; a request to a public URL resumes a paused box | No; a stopped sandbox is started by API |
| Fork | Fork a hibernated sandbox from its snapshot, or a running one sharing its memory | Snapshot a running box and start many new boxes from it | Fork a running sandbox with its disk |
| Shell access | Terminals, commands and files through the SDK; no SSH | SDK commands, plus SSH through a gateway | 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 | HTTPS URL per port, public unless you add a token or basic auth; no raw TCP | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; a dedicated IPv6 or IPv4 |
| Desktop and browser | No desktop; a headless Chromium template | Managed headless Chromium with AI page actions and CDP; no desktop | Linux desktop streamed at 60fps, Chromium and computer-use tools |
| Coding agents | Run your own agent through the command API | Claude Code, Codex and OpenCode built in, with run and stream APIs, webhooks and scheduled prompts | Claude Code, Codex and other agents preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Secrets passed in as environment variables | Host proxy injects headers into outbound HTTPS on port 443; set when the box is created | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Outbound rules | No outbound allowlist documented | Allow all, deny all, or allow and deny by domain and CIDR, changeable on a running box | Open internet, no provider-side allowlist |
Every feature Battleships tracks (43)
| Feature | CodeSandbox SDK | Upstash Box | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | No | Yes |
| Docker inside | Yes | No | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Not published | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | No | Yes |
| Browser | No | Yes | Yes |
| Computer-use API | No | No | Yes |
| SSH | No | Yes | 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 | 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 | Yes | No |
| Wake on request | Yes | Yes | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | No | 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 | Yes | 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 | Yes | Yes |
| Audit logs | Not published | Not published | No |
| SSO | Yes | No | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | No | No | No |
| EU data residency | No | No | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
Neither CodeSandbox SDK nor Upstash Box has a result in the hpc-sandbox-benchmarks CPU test, so there is no comparable measurement between them. 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. CodeSandbox SDK and Upstash Box 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 | Upstash Box, 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 | $21 · 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 | $21 · Pay as You Go | $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 | $900 · 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 | $306 · Pay as You Go | $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 | $1,822 · Pay as You Go | $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 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.
Upstash Box: A standard box is billed for the CPU it actually uses, at $0.10, $0.20 or $0.40 per active CPU hour by size, plus $0.10 per GB-month of storage, and RAM is free. A keep-alive box costs a flat $8, $16 or $32 a month whether busy or not.
Upstash Box: 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
CodeSandbox SDK's Scale plan allows 250 VMs at once, so the user-sandboxes and 1,000-job scenarios do not fit it without Enterprise, and each VM has a 20 GB disk. Upstash Box allows 1,000 boxes at once, but it cannot run Docker inside, so the 50-agent scenario does not fit there. Neither publishes an egress price. boat's limit is start rate: for 1,000 short jobs at once, even the $2,000 plan queues starts.
| Scenario | CodeSandbox SDK | Upstash Box | 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
you need Docker inside each sandbox and want it to hibernate with its memory and wake on the next request, and you are fine building on what Together now calls its legacy SDK.
- Docker inside a real VM. For agents that run databases or build images: each Firecracker VM has its own kernel, root and Docker.
- Memory hibernation and forks. For work used in bursts: a sandbox sleeps with its memory and wakes or forks with processes still running.
- Bigger machines on Enterprise. For very large single jobs: Enterprise offers sizes up to 64 cores and 128 GB.
Use Upstash Box when
your agents mostly wait, you want a coding agent ready in each box, you need strict outbound rules, or you run big bursts in the US.
- A coding agent built in. For teams that want Claude Code, Codex or OpenCode ready in each box, with streaming, webhooks and scheduled prompts.
- Idle costs no CPU. For agents that mostly wait: only used CPU is billed, RAM is free, and a request wakes a paused box.
- Outbound rules and big bursts. For locked-down or bursty work: allow lists by domain or CIDR, and 1,000 boxes at once by default.
Where boat fits
If your agents do long, real work, look at boat. Each sandbox is a full VM with SSH, Docker, systemd and /dev/kvm, a 60fps desktop, coding agents built in and a credentials proxy, so you get the parts CodeSandbox SDK and Upstash Box each leave out in one machine.
A whole machine with Docker and KVM
An Upstash box cannot run Docker, so agents that start a database or build an image get stuck. CodeSandbox SDK runs Docker but has no SSH and no documented /dev/kvm, so Android emulators and nested VMs cannot start.
A desktop the agent can see
Both give only a headless Chromium, so a computer-use agent cannot click desktop apps or native dialogs, and no human can watch along. boat streams a full Linux desktop at 60fps with computer-use tools.
Agents and keys set up for you
On CodeSandbox SDK you build the agent harness yourself and pass keys in as environment variables the agent can read. Upstash has agents and a header proxy, but its proxy is fixed when the box is created.
Use boat when your agents need a real machine for hours: Docker, emulators, a desktop, SSH, a big disk and servers others can reach, with the agent and its keys already set up. Compare it one to one: boat vs CodeSandbox SDK and boat vs Upstash Box.
Questions people ask
Is CodeSandbox SDK cheaper than Upstash Box?
Usually not. For one coding agent on workdays, CodeSandbox SDK comes to $193 a month against $21 on Upstash, and for one agent that never stops, $341 against $21. For 1,000 short jobs at once, Upstash comes to $1,822 a month and fits, while CodeSandbox SDK's Scale plan caps at 250 VMs.
Which is faster, CodeSandbox SDK or Upstash Box?
There is no comparable CPU measurement for either one. boat did 26.69 runs per second on the hpc-sandbox-benchmarks Node.js loop at 4 vCPU / 8 GB, but neither CodeSandbox SDK nor Upstash Box was part of that run.
Can CodeSandbox SDK and Upstash Box run Docker?
CodeSandbox SDK runs Docker with root inside each Firecracker VM. Upstash Box does not document it: each box is itself a Docker container, and custom images are listed as coming soon. boat runs Docker and systemd in every sandbox.
Which has coding agents built in?
Upstash Box ships Claude Code, Codex and OpenCode with run and stream APIs. On CodeSandbox SDK you run your own agent through the command API. boat preinstalls Claude Code, Codex and others, driven from outside with a prompt, steer and events API.
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.
Can either one run a desktop for computer use?
No. CodeSandbox SDK has a headless Chromium template, and Upstash gives a managed headless Chromium with a CDP endpoint, with no desktop. boat streams a full Linux desktop at 60fps with computer-use tools.
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs CodeSandbox SDK
- boat vs Upstash Box
- 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