CodeSandbox SDK vs Beam
CodeSandbox SDK gives each sandbox a Firecracker microVM that hibernates with its memory and wakes on the next HTTP request. Beam is a serverless GPU platform whose sandboxes are quick gVisor containers, with a separate line of CPU VMs.
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.
Beam
Beam is a serverless cloud for GPU inference, sandboxes and background jobs, built on its open-source runtime Beta9.
Beam runs functions, REST endpoints, task queues, pods, sandboxes and VMs on CPUs and GPUs, all from a Python or TypeScript SDK. A sandbox is a container isolated with gVisor that starts in a second or two, lives until you terminate it or its time to live runs out, and can be saved as a filesystem image or a memory snapshot. Beam VMs are a separate CPU product: a microVM with its own kernel, systemd and a root disk that stays when it stops. Much of Beam is a GPU serverless platform for AI teams.
- Bring your own cloud
- Management fee per vCPU and GB of RAM, on top of your own cloud bill
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 | Beam: 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, systemd, /dev/kvm and a disk that stays, which boat gives every sandbox; Beam sandboxes end with their time to live and CodeSandbox SDK documents no /dev/kvm. | 178th of 367, with limits $1,939 a month | 69th of 367, with limits $551 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 | 115th of 366, with limits $651 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 fit short code runs: Beam ranks 8th with sandboxes that start in a second or two and end on a timer, and CodeSandbox SDK ranks 46th with VMs that hibernate between runs. | 46th cheapest of 345 $642 a month | 8th cheapest of 345 $117 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 Beam ranks 3rd and boat ranks 1st, while CodeSandbox SDK's Scale plan caps at 250 VMs at once, below the 300 this use case needs. | 140th of 361, with limits $1,707 a month | 3rd cheapest of 361 $290 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 can fork a running VM that shares its memory, and Beam can restore a memory snapshot into new sandboxes, so both can branch rollouts from one warm state. | 348th of 360, with limits $3,861 a month | 341st of 360, with limits $939 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 | 13th cheapest of 364 $251 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 run CI jobs with Docker, but builds of Android apps or VM images need /dev/kvm, which boat has and neither CodeSandbox SDK nor Beam documents. | 92nd cheapest of 377 $860 a month | 12th cheapest of 377 $171 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A Beam VM keeps its root disk while stopped and costs no compute then, and boat saves the disk every minute and on stop; CodeSandbox SDK is a compromise here. | 310th of 368, with limits $240 a month | 13th cheapest of 368 $21 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 CodeSandbox SDK nor Beam has a desktop for computer use, while boat streams a Linux desktop at 60fps with Chromium. | 206th of 369, with limits $691 a month | 111th of 369, with limits $237 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 | 195th of 367, with limits $176 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 | 200th of 346, with limits $131 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 | 42nd of 338, with limits $923 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 | 175th of 360, with limits $155 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 Beam has GPUs, from RTX 4090 up to H100 and B200; CodeSandbox SDK and boat are CPU only. | Can't run it | Cheapest of 98 $458 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 | Beam | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | gVisor container by default for sandboxes; separate Beam VMs are CPU microVMs with their own kernel | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Nested virtualization | Not documented | Not documented | Yes, /dev/kvm for Android emulators and VMs |
| Docker and systemd | Docker and root; built from any Dockerfile | Docker inside sandboxes with docker_enabled; systemd only in Beam VMs, not in sandboxes | Docker, systemd and root, like a normal Ubuntu server |
| Lifetime | No hard cap; hibernates after an idle timeout of up to one day | Default 10 minutes; set -1 to run until you terminate it | No session cap on paid plans; you set the time to live |
| Pause and resume | Hibernates with a memory snapshot; resumes with processes still running | A sandbox ends with its time to live unless you save an image or snapshot; a Beam VM keeps a 50 GiB root disk while stopped | Disk is 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 | Memory snapshot of a running sandbox with its processes, restored into new sandboxes | Fork a running sandbox with its disk |
| Wake on request | Yes; an HTTP request to a host wakes a hibernated VM | No | No; a stopped sandbox is started by API |
| Biggest machine | Up to 16 cores / 32 GB on Scale, 64 cores / 128 GB on Enterprise | Maximum sandbox size not published | Up to 16 vCPU / 32 GB on the $100 plan and above |
| GPUs | No | GPU sandboxes and serverless GPUs up to H100, H200 and B200 | No, CPU only |
| Desktop and browser | No desktop; a headless Chromium template | No desktop or browser product | Linux desktop streamed at 60fps with Chromium and computer use |
| Inbound access | HTTPS host per port, public by default, signed tokens for private hosts; no raw TCP or public IP | HTTPS URL per exposed port, public with no built-in auth; no raw TCP or dedicated IP | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6 |
| Coding agents | Run your own agent through the command API | None preinstalled; you install and run them through process exec | Claude Code, Codex and others preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Secrets passed in as environment variables | Secrets exposed as environment variables inside the sandbox | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Regions and self-hosting | A country hint steers scheduling, not guaranteed; no self-hosting | US only; Beta9 runtime is AGPL-3.0 and free to self-host, or bring your own cloud for a fee | EU only (Germany, Finland, France); no self-hosting |
Every feature Battleships tracks (43)
| Feature | CodeSandbox SDK | Beam | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | No | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | No | 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 | No | Yes |
| Automatic snapshots | Yes | No | 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 | No | 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 | No | Yes |
| Secret proxy for any API | No | No | Yes |
| Preinstalled agents | No | No | Yes |
| Agent harness API | No | No | Yes |
| MCP server | No | Yes | No |
| GPU | No | Yes | No |
| Windows | No | No | No |
| Arm64 | No | No | No |
| Self-hosting | No | Yes | No |
| BYOC | No | Yes | No |
| Open source | No | Yes | 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 | No | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | No | Yes | No |
| EU data residency | No | Not published | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable CPU measurement for CodeSandbox SDK or Beam: neither has a result on the StarSling hpc-sandbox-benchmarks test, so we cannot say which is faster at CPU work. boat did 26.69 runs per second on that test at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts. Beam's own guide says its sandboxes cold-boot in 1 to 3 seconds.
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 Beam 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 | Beam, 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 | $5 · Developer | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $341 · Scale | $22 · Developer | $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 | $410 · Team | $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 | $191 · Team | $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 | $259 · Team | $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. Scale adds a $170 monthly platform fee that is not usage credit, and a hibernated VM costs nothing.
Beam: Beam sandboxes bill per second for each CPU core and GiB of RAM until you terminate them or their time to live ends, and Beam VMs cost no compute while stopped. Team costs $89 a month plus usage, with no usage credit and no egress fees.
Beam: 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 its price for disk beyond 20 GB and for egress is not published. Beam's Developer plan allows 30 CPU containers at once, so 50 parallel agents need Team, and Beam publishes no price for disk beyond what a VM includes. boat's start limits bite on bursts: at 1,000 short jobs at once its $2,000 plan queues starts, while Beam's Team plan fits.
| Scenario | CodeSandbox SDK | Beam | 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, and you are fine building on what Together now calls its legacy SDK.
- Memory hibernation and wake on request. For sandboxes that sleep between visits: an HTTP request wakes a hibernated VM with its processes still running.
- Forks that share memory. Good for branching many runs from one warm state, by forking a running VM while it shares memory with its parent.
- Bigger machines on Enterprise. Teams that need very large single machines can get up to 64 cores and 128 GB through Enterprise.
Use Beam when
your work needs GPUs, when you want quick short-lived sandboxes or low-cost CPU VMs in the US, or when you must self-host.
- GPUs in the same platform. For work that needs a GPU, Beam offers GPU sandboxes and serverless GPUs from RTX 4090 up to H100, H200 and B200.
- Quick sandboxes with outbound rules. Sandboxes start in a second or two, and you can block all outbound traffic or allow up to 10 CIDR ranges.
- Open source and your own cloud. Its Beta9 runtime is AGPL-3.0 and free to self-host, and Beam can also run in your own cloud for a fee.
Where boat fits
If your agents work for hours on installs, builds, Docker, emulators and a browser, both CodeSandbox SDK and Beam leave pieces for you to build. boat gives every sandbox a full VM with /dev/kvm, systemd, a 60fps desktop, coding agents and a credentials proxy already set up. Pick Beam instead if you need GPUs, and CodeSandbox SDK if you need memory hibernation that wakes on request.
A full machine with /dev/kvm and systemd
Neither CodeSandbox SDK nor Beam documents /dev/kvm, so Android emulators and nested VMs cannot start, and a Beam sandbox has no systemd unless you move to its separate VM product.
Hosting that is private by default, plus raw TCP
Both serve HTTPS only, public by default, and Beam has no built-in auth on sandbox URLs. A database or game server an agent starts over plain TCP cannot be reached on either.
Agents, desktop and keys built in
On both you install the agent harness yourself, neither has a desktop for computer use, and API keys sit as environment variables inside a machine the agent controls, where one prompt injection can leak them.
Use boat when your agents do real work over hours or days: installs, builds, Docker, emulators and a browser on a full VM with the agent and its keys already set up. Compare it one to one: boat vs CodeSandbox SDK and boat vs Beam.
Questions people ask
Is CodeSandbox SDK cheaper than Beam?
No. Beam costs less in all five scenarios on this page, for example $22 against $341 a month for one agent that never stops, and $410 against $2,500 a month for 50 agents in parallel. CodeSandbox SDK's Scale plan also does not fit the two scenarios that need more than 250 VMs at once.
Which is faster, CodeSandbox SDK or Beam?
We have no comparable CPU measurement for either, so we cannot say. Beam's guide says its sandboxes cold-boot in 1 to 3 seconds, and CodeSandbox SDK resumes a hibernated VM from its memory snapshot.
Can CodeSandbox SDK and Beam run Docker?
Yes. CodeSandbox SDK runs Docker with root and builds sandboxes from any Dockerfile, and Beam supports Docker inside a sandbox with docker_enabled. boat runs Docker too, plus systemd and /dev/kvm for emulators and VMs.
Is a Beam sandbox a VM like CodeSandbox SDK?
Not by default. Beam's sandboxes are containers using gVisor, while each CodeSandbox SDK sandbox is a Firecracker microVM. Beam also sells separate CPU VMs with their own kernel and systemd.
Does either have GPUs?
Only Beam. It offers GPU sandboxes and serverless GPUs from RTX 4090 up to H100, H200 and B200. CodeSandbox SDK and boat are CPU 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 Beam
- 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