Together Code Sandbox vs Instabox
Together Code Sandbox starts VMs from Docker-image snapshots, in sizes from a tenth of a core, and can save their memory to start many copies. Instabox, an invite-only beta that launched on 2026-10-14, gives each agent one 4 vCPU / 8 GiB microVM with SSH, Docker and a desktop.
The companies and products
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.
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. “65th cheapest of 367” means 64 of the other 366 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 | Together Code Sandbox: 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 A software factory needs Docker and root: Instabox documents Docker and Compose inside, Together's new SDK does not document Docker inside, and boat adds /dev/kvm and forks of running sandboxes. | 65th of 367, with limits $528 a month | No published price | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that stays on its machine all month needs a box that keeps running; Instabox pauses after 30 idle minutes unless you turn that off, and Together sandboxes have no idle detection or wake on request. | 152nd of 366, with limits $1,095 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 For short Python runs, Together's Code Interpreter bills per 60-minute session with no VM to manage; Instabox documents no separate code interpreter. | 326th of 345, with limits $2,190 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 Instabox allows 5 machines per account, paused and stopped ones included, so it cannot give a sandbox to each of many users today; Together's VMs need Together to enable them for your organization. | 234th of 361, with limits $900 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 Together can save a sandbox with its memory and start many copies from it, which suits rollouts that branch from one warm state; Instabox snapshots keep only the disk. | 315th of 360, with limits $21,900 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 limits how many evals run at once, and Together documents a Harbor guide for agent evals on its VMs. | 258th of 364, with limits $450 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 | 251st of 377, with limits $180 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 works as a cloud dev box with SSH and mosh, while Together offers no SSH, only commands and shells through its SDK and CLI. | 210th of 368, with limits $22 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 Computer-use agents need a desktop: Instabox has one on a single template with a screenshot and click API, Together has none, and boat streams one at 60fps in every sandbox. | 184th of 369, with limits $600 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 | 301st of 367, with limits $900 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 | 219th of 346, with limits $180 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 | 124th of 338, with limits $3,600 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 | 167th of 360, with limits $150 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 | Together Code Sandbox | Instabox | boat |
|---|---|---|---|
| Isolation | A VM per sandbox on Together's infrastructure | Firecracker microVM with its own kernel and root | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Getting access | The SDK and CLI must be enabled for your organization by Together | Invite-only beta; sign in with GitHub or Google | Sign up and start a sandbox from the API, CLI or dashboard |
| Machine size | 0.1 to 16 cores, 1 to 8 GB of memory per core; disk size fixed | One size for everyone: 4 vCPU / 8 GiB with 20 GB storage | Several sizes, up to 16 vCPU / 32 GB on the $100 plan and above |
| Docker and root | Commands run as user 1000 by default, root on request; Docker inside not documented | Root, with Docker and Docker Compose inside | Docker, systemd and root on every machine |
| Nested virtualization | Not documented | Not documented | Yes, /dev/kvm for Android emulators and VMs |
| Shell access | Commands, interactive shells and files through the SDK and CLI; no SSH | SSH through a gateway with short-lived certificates, paste-anywhere SSH tokens and mosh | SSH, plus exec and files over the API |
| Saving memory | End a sandbox with a snapshot of disk and memory; new sandboxes start with processes running | Pause keeps memory and running programs, usually resumes in about a second; snapshots keep the disk only | No memory save; disk saved every minute and on stop, and resume boots the machine again |
| Fork | No live fork: the parent stops, then you start many sandboxes from its snapshot | Fork copies a stopped machine only | Fork a running sandbox; the original keeps running |
| Idle and lifetime | Time to live counts from creation; no idle detection and no wake on request | Pauses after 30 idle minutes by default, which you can change or turn off; a visit does not wake it | Runs until you stop it or its time to live ends; started again by API |
| Reaching the sandbox | All ports public; preview URLs coming soon; an experimental inbound allowlist by IP or token | HTTPS on up to 16 ports, open to anyone with the URL; offline while the machine is paused | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv6 or IPv4 |
| Desktop and computer use | None; headless command and file access only | Linux desktop with a browser on one template, screenshot and click API, shareable view or control links | 60fps Linux desktop with Chromium and a computer-use agent in every sandbox |
| Coding agents | Run your own agent through execs; a Harbor guide for agent evals | Templates and saved agent sign-ins in snapshots; you run the agent yourself | Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | No credentials proxy documented | 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 | Not published | Not published | EU only (Germany, Finland, France) |
Every feature Battleships tracks (43)
| Feature | Together Code Sandbox | Instabox | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Not published | 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 | No | No | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | No | No | Yes |
| Memory fork | Yes | No | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | No | Yes | No |
| Wake on request | No | 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 | Yes | 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 | Yes | Not published | Yes |
| Usage per sandbox (API) | Yes | 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 | Not published | Not published | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
Neither Together Code Sandbox 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 test at 4 vCPU / 8 GB. Instabox says a new machine's shell is ready 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. Together Code Sandbox 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 | Together Code Sandbox, 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 | $5 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | No published price | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $22 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | 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 | $264 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | 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 | $900 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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 | $6,000 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | No published price | $2,000 · $2000/mo · with limits |
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 uses Code Interpreter: $0.03 per 60-minute session from prepaid credits, which runs only Python and keeps no disk.
Instabox: Instabox is free during the beta, with 5 machines per user, and publishes no price yet, so no bill can be compared.
Instabox: Plans start at $20 a month, and the whole fee becomes usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
The Together column is Code Interpreter, so its limits decide every row: sessions end after an hour, nothing is kept, and the machine size is not published. Instabox has no published rate, and it allows 5 machines per account, paused and stopped ones included, each 4 vCPU / 8 GiB with API exec calls of at most 10 minutes, 4 at once; the 50-agent and user-sandbox scenarios do not fit it today. On boat the limit that bites is starts: 1,000 short jobs at once need more starts per hour and per day than the $2,000 plan allows, so they are queued.
| Scenario | Together Code Sandbox | 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 Together Code Sandbox when
you already run models on Together and want sandboxes in many sizes that 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.
- Sizes from a tenth of a core. For many light jobs or a bigger build: sandboxes go from 0.1 to 16 cores, with 1 to 8 GB per core.
- Sandboxes next to your models. For teams already on Together: sandboxes, a Python runner and model calls share one account and API key.
Use Instabox when
you want to try a few 4 vCPU / 8 GiB agent machines during its free beta, with SSH, mosh, Docker and a desktop.
- SSH with mosh. For people who live in a terminal: SSH through a gateway, mosh relay and paste-anywhere tokens, which Together does not offer.
- Docker and Compose documented. For agents that run stacks: each machine has root with Docker and Docker Compose inside.
- A desktop for computer use. For computer-use tests: one template has a Linux desktop with a browser and a screenshot and click API.
Where boat fits
Look at boat when your agents do long, real work: builds, Docker, emulators and servers that other people reach. boat gives each one a full machine you can sign up for today, with coding agents you drive from outside and API keys kept in a credentials proxy outside the sandbox.
A whole machine with /dev/kvm
Android emulators and VM-based tests need nested virtualization, which neither Together nor Instabox documents. Together also runs commands as a normal user and does not document Docker inside, and Instabox has one 4 vCPU / 8 GiB size.
Fork work that is still running
To branch a task midway, Together stops the parent and starts copies from its snapshot, and Instabox forks only a stopped machine. Either way the running programs end; on boat the original keeps working.
Port URLs that are private by default
Together makes every port public with preview URLs still coming, and Instabox URLs are open to anyone who has them. A half-built app or database needs your own login in front; boat URLs carry a token, on up to 50 ports.
Use boat when your agents need a full machine with /dev/kvm, forks of running work, private port URLs and more than five at once, on a service you can sign up for today. Compare it one to one: boat vs Together Code Sandbox and boat vs Instabox.
Questions people ask
Is Together Code Sandbox cheaper than Instabox?
It can't be compared yet. Instabox is free during its beta and publishes no price, so there is no bill to set against Together's. Together's only self-serve price is Code Interpreter, $0.03 per 60-minute session.
Which is faster, Together Code Sandbox or Instabox?
Neither has been measured on the same CPU test, 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. boat scored 26.69 runs per second at 4 vCPU / 8 GB.
Can Together Code Sandbox or Instabox run Docker?
Instabox's docs say Docker and Docker Compose run inside each machine, with root. Together builds sandboxes from Docker images, but its new SDK does not document Docker inside a sandbox. boat runs Docker, systemd and root on every machine.
Can I SSH into Together Code Sandbox or Instabox?
Instabox has SSH through a gateway with short-lived certificates, plus mosh and paste-anywhere SSH tokens. Together has no SSH; you run commands and shells through its SDK and CLI. boat has SSH into every sandbox.
Can I start using either one today?
Not freely. Together's VMs must be enabled for your organization, and Instabox is an invite-only beta that launched on 2026-10-14. boat is open to sign up, with plans from $20 a month.
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
More comparisons
- boat vs Together Code Sandbox
- boat vs Instabox
- E2B vs Together Code Sandbox
- Daytona vs Together Code Sandbox
- Modal vs Together Code Sandbox
- Vercel Sandbox vs Together Code Sandbox
- Cloudflare Sandbox vs Together Code Sandbox
- Blaxel vs Together Code Sandbox
- Runloop vs Together Code Sandbox
- Tensorlake vs Together Code Sandbox
- Morph Cloud vs Together Code Sandbox
- CodeSandbox SDK vs Together Code Sandbox