CodeSandbox SDK vs Instabox
Both start a Firecracker microVM for each sandbox. CodeSandbox SDK hibernates VMs with their memory, wakes them on the next HTTP request and runs up to 250 at once on Scale, while Instabox is a free invite-only beta with SSH, mosh and a desktop on 5 machines of one size.
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.
Instabox
Instabox, made by InsForge, gives each AI agent its own Linux computer in the cloud. It launched on 2026-10-14 as an invite-only beta.
Each Instabox machine is a Firecracker microVM with its own kernel, root and Docker, started from one of four templates (agent-browser, universal, herdr or orca) or from your own snapshot. Every machine is 4 vCPU / 8 GiB with 20 GB of storage, and you drive it from a CLI, a TypeScript SDK or an HTTP API, with SSH, mosh, public port URLs and a desktop for computer use. It is aimed at developers who want a cloud box for a coding agent.
- Isolation
- Firecracker microVM per machine
- Machines per account
- 5, in any state: paused and stopped ones count
- Company
- InsForge AI, Inc.
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 | Instabox: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Neither CodeSandbox SDK nor Instabox documents /dev/kvm or forks that keep a running machine going, which a software factory leans on; boat ranks 3rd here. | 178th of 367, with limits $1,939 a month | No published price | 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 | No published price | 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 suits short code runs on VMs that hibernate with their memory and wake on the next request; Instabox publishes no rate, so it is not ranked. | 46th cheapest of 345 $642 a month | No published price | 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 and runs up to 250 at once on Scale, while Instabox allows 5 machines per account; boat ranks first. | 140th of 361, with limits $1,707 a month | No published price | 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 one running state, while Instabox forks only a stopped machine. | 348th of 360, with limits $3,861 a month | No published price | 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 Instabox's 5-machine cap, paused and stopped ones included, limits how many evals run at the same time; CodeSandbox SDK allows 250 on Scale. | 64th cheapest of 364 $1,335 a month | No published price | 10th cheapest of 364 $200 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI jobs that build Android apps or VM images need /dev/kvm, which boat exposes and neither CodeSandbox SDK nor Instabox documents. | 92nd cheapest of 377 $860 a month | No published price | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Instabox gives a dev box SSH and mosh, CodeSandbox SDK has no SSH, and boat has SSH on a published plan. | 310th of 368, with limits $240 a month | No published price | 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 CodeSandbox SDK has no desktop; Instabox has a desktop with a screenshot and click API where you bring the model, and boat streams one at 60fps with a computer-use agent. | 206th of 369, with limits $691 a month | No published price | 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 | No published price | 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 | No published price | 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 | No published price | 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 | No published price | 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 | No published price | 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 | No published price | Can't run it |
Key features
| Feature | CodeSandbox SDK | Instabox | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | Firecracker microVM with its own kernel and root | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Machine sizes | 2 to 16 cores self-serve, up to 32 GB on Scale; up to 64 cores and 128 GB on Enterprise | One size for everyone: 4 vCPU / 8 GiB with 20 GB storage; other sizes are refused | Several sizes, up to 8 vCPU / 16 GB on the $20 plan and 16 vCPU / 32 GB on $100 and above |
| Machines at once | 10 on the free Build plan, 250 on Scale, more on Enterprise | 5 per account, and paused and stopped ones count | 300 at once fits the user-sandbox scenario; starts per hour and per day are capped on big bursts |
| Pause and resume | Hibernates with a memory snapshot; resumes with processes still running | Pause keeps memory and running programs; the docs say resume usually takes about a second | Stop keeps the disk, saved every minute; start boots the machine again |
| Wake on request | Yes; an HTTP request to a host wakes a hibernated VM | No; port URLs go offline while a machine is paused, and a visit does not wake it | No; a stopped sandbox is started by API |
| Fork | Fork a hibernated sandbox from its snapshot, or a running one sharing its memory | Fork copies a stopped machine only | Fork a running sandbox with its disk |
| Nested virtualization | Not documented | Not documented | Yes, /dev/kvm for Android emulators and VMs |
| Docker and root | Docker and root; built from a template or any Dockerfile | Docker and Docker Compose with root; started from one of four templates or your own snapshot | Docker, systemd and root |
| Shell access | Terminals, commands and files through the SDK; no SSH | SSH through a gateway with short-lived certificates, paste-anywhere SSH tokens and mosh | 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 or public IP | HTTPS on up to 16 ports, open to anyone with the URL; offline while the machine is paused | HTTPS on up to 50 ports, token-protected by default; raw TCP; a dedicated IPv6 or IPv4 |
| Desktop and computer use | No desktop; a headless Chromium template | Linux desktop with a browser on one template, screenshot and click API, shareable view or control links; you bring the model | Linux desktop streamed at 60fps with Chromium and a computer-use agent |
| Coding agents | Run your own agent through the command API | Templates and saved agent sign-ins in snapshots; you run the agent yourself | Seven agents preinstalled, including Claude Code and Codex, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Secrets passed in as environment variables | Vault writes your secrets into each machine as environment variables or files | Credentials proxy: real keys never enter the sandbox, for model providers and any HTTPS API |
| Regions | A country hint steers scheduling, for example to Europe, but placement is not guaranteed | Not published | EU only (Germany, Finland, France) |
Every feature Battleships tracks (43)
| Feature | CodeSandbox SDK | Instabox | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | Not published | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | Yes | Yes |
| Browser | No | Yes | Yes |
| Computer-use API | No | Yes | 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 | No | 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 | No | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | Not published | No |
| Secret proxy | No | No | Yes |
| Secret proxy for any API | No | No | Yes |
| Preinstalled agents | No | Not published | Yes |
| Agent harness API | No | Not published | Yes |
| MCP server | No | Not published | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | No | Not published | No |
| Self-hosting | No | Not published | No |
| BYOC | No | Not published | No |
| Open source | No | No | No |
| Scoped API keys | Not published | Yes | 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 | Not published | No |
| HIPAA | No | Not published | No |
| EU data residency | No | Not published | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
Neither CodeSandbox SDK nor Instabox has a comparable CPU measurement, so this page makes no speed claim between them. boat did 26.69 runs per second on the StarSling hpc-sandbox-benchmarks Node.js loop at 4 vCPU / 8 GB. Instabox says you are in a new machine's shell in under a second; that has not been measured.
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 Instabox 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 | Instabox, 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 | No published price | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $341 · Scale | No published price | $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 | No published price | $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 | No published price | $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 | No published price | $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. Scale adds a $170 monthly platform fee that is not usage credit, and a hibernated VM costs nothing.
Instabox: Instabox is free during the beta, with 5 free machines per user, and publishes no price yet, so no bill can be compared with CodeSandbox SDK or boat.
Instabox: 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 the price for disk beyond 20 GB and for egress is not published. Instabox allows 5 machines per account, paused and stopped ones included, with an API exec call capped at 10 minutes and 4 at once, so the 50-agent and user-sandbox scenarios do not fit it, and none of the scenarios can be priced. boat fits four of the five, but at 1,000 short jobs at once even its $2,000 plan queues starts.
| Scenario | CodeSandbox SDK | Instabox | 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, or you need hundreds at once, and you are fine building on what Together now calls its legacy SDK.
- Wake on the next request. For previews used in bursts: an HTTP request wakes a hibernated VM with its memory and running processes intact.
- Forks that share memory. For rollouts or test variants: fork a running sandbox that shares memory with its parent, or a hibernated one from its snapshot.
- More machines and bigger sizes. For fleets: Scale runs 250 VMs at once in sizes up to 16 cores and 32 GB, and Enterprise goes to 64 cores.
Use Instabox when
you want to try a few free 4 vCPU / 8 GiB agent machines during its invite-only beta, with SSH, mosh and a desktop.
- Free during the beta. For trying things out: each account runs 5 machines of 4 vCPU / 8 GiB for free while the beta lasts.
- SSH with mosh. For people who live in a terminal: SSH through a gateway, mosh that survives sleep, and paste-anywhere SSH tokens.
- A desktop to drive. For computer-use experiments: a Linux desktop with a browser, a screenshot and click API, and shareable view or control links.
Where boat fits
If your agents do hours of real work, both options leave gaps: neither documents nested virtualization, neither documents raw TCP or keeps port URLs private by default, and on both you set up the agent and put its keys inside. boat gives each agent a full VM with the agent, a desktop and a credentials proxy already there, with published plans in the EU.
A whole machine with /dev/kvm
Neither CodeSandbox SDK nor Instabox documents nested virtualization on its Firecracker VMs, so Android emulator builds and VM-based tests cannot count on starting. CodeSandbox SDK also has no SSH. boat has SSH, systemd, Docker and /dev/kvm.
Private URLs and raw TCP
CodeSandbox SDK hosts are HTTPS only and public unless you sign them private; Instabox port URLs are open to anyone with the link and go offline while paused. boat serves 50 ports with a token by default, plus raw TCP.
Agents and keys set up for you
On both, you install and run the agent yourself, and its keys sit inside the machine as environment variables or files, where one prompt injection can leak them. boat preinstalls seven agents with an API and keeps real keys in a proxy outside.
Use boat when your agents need a full machine with /dev/kvm, forks of running work, private URLs, a built-in agent and keys kept outside, on plans that are published today. Compare it one to one: boat vs CodeSandbox SDK and boat vs Instabox.
Questions people ask
Is CodeSandbox SDK cheaper than Instabox?
It can't be compared yet. Instabox is free during the beta, with 5 free machines per user, and publishes no price. CodeSandbox SDK bills credits per started minute; one coding agent on workdays comes to $193 a month on Scale.
Which is faster, CodeSandbox SDK or Instabox?
Neither has a comparable CPU measurement, so there is no answer from data. Instabox says a new machine's shell is ready in under a second, and its docs say a paused machine usually resumes in about a second; neither has been measured here. boat did 26.69 runs per second on the same benchmark at 4 vCPU / 8 GB.
Can CodeSandbox SDK and Instabox run Docker?
Yes, both run Docker with root inside the VM, and Instabox also documents Docker Compose. Neither documents nested virtualization, so Android emulators are not a safe bet on either. boat runs Docker and exposes /dev/kvm.
Can I SSH into CodeSandbox SDK or Instabox?
Instabox, yes: SSH goes through a gateway with short-lived certificates, and it relays mosh. CodeSandbox SDK has no SSH; you use terminals, commands and files through its SDK. boat has SSH in every sandbox.
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 anyone sign up for Instabox?
Instabox, made by InsForge, launched on 2026-10-14 as an invite-only beta. You sign in with GitHub or Google, and each account gets up to 5 machines.
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs CodeSandbox SDK
- boat vs Instabox
- 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