exe.dev vs Together Code Sandbox
exe.dev rents Linux VMs you keep, reach over SSH and boot from your own Docker image, in nine regions. Together Code Sandbox starts VMs from Docker-image snapshots through an SDK and can save their memory when they end. Together must enable it for your organization.
The companies and products
exe.dev
exe.dev, made by Bold Software, Inc., rents Linux VMs for developers and AI agents that you reach over SSH and HTTPS.
You reserve a pool of vCPUs and memory, and your VMs share it. You can also start standalone VMs billed by the second. Each VM is KVM-isolated with Cloud Hypervisor, boots from a container image in about two seconds, and has root, systemd and Docker. It comes with Claude Code, Codex, Pi and exe.dev's own Shelley agent. It suits developers who want a persistent dev box or a sandbox for their agents.
- Company
- Bold Software, Inc.
- Preinstalled agents
- claude, codex, pi and the Shelley web agent
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 Together must enable it for your organization. The pricing page also lists Code Interpreter at $0.03 per 60-minute session.
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. “20th cheapest of 361” means 19 of the other 360 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 | exe.dev: price rank | Together Code Sandbox: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month | 267th of 365, with limits $3,721 a month | 67th of 365, with limits $528 a month | 5th cheapest of 365 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB exe.dev fits an always-on assistant, with a VM that runs until you stop it. A Together sandbox runs until you end it or its time to live ends, with no idle detection or wake on request, so your backend starts and stops it. boat fits with auto-stop off on a paid plan (default 1 hour). | 20th cheapest of 361 $3,833 a month | 107th of 361, with limits $1,095 a month | 6th cheapest of 361 $657 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Together's pricing page lists Code Interpreter at $0.03 per 60-minute session. exe.dev and boat are not built for many tiny runs. | 231st of 336, with limits $175 a month | 318th of 336, with limits $2,190 a month | 189th of 336, 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 exe.dev Personal stops at 50 VMs in total. On Together every port URL is public unless you set an experimental access policy. boat's HTTPS URLs are token-protected by default, within its plan's start limits. | 252nd of 349, with limits $1,234 a month | 231st of 349, with limits $900 a month | 3rd cheapest of 349 $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. exe.dev copies a VM's disk with cp. boat forks a running sandbox from its last 1-minute disk snapshot, without memory. | 260th of 349, with limits $5,250 a month | 309th of 349, with limits $21,900 a month | 39th of 349, with limits $2,000 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month Together and boat both document a Harbor integration for agent evals. exe.dev runs other agents through its exec API. boat ships seven agents with an API to prompt, steer and follow each run. | 280th of 359, with limits $1,050 a month | 260th of 359, with limits $450 a month | 10th cheapest of 359 $200 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month exe.dev standalone VMs bill per second, and pools bill whether used or not. Together bills per vCPU-hour and GiB-hour once it enables the product. boat bills per second while a sandbox runs, and each job counts as a start. | 289th of 374, with limits $504 a month | 253rd of 374, with limits $180 a month | 2nd cheapest of 374 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB exe.dev is a 24/7 dev box with SSH and a disk that lasts. Together documents no SSH. boat matches exe.dev here and adds a desktop in the browser. | 24th cheapest of 371 $35 a month | 226th of 371, with limits $22 a month | 19th cheapest of 371 $26 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Neither exe.dev nor Together has a built-in desktop. On both you install a desktop and a browser yourself. boat streams a built-in 60 fps desktop with Chrome. | 270th of 367, with limits $1,055 a month | 105th of 367, with limits $600 a month | 7th cheapest of 367 $200 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month | 187th of 356, with limits $530 a month | 195th of 356, with limits $900 a month | 7th cheapest of 356 $200 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 187th of 343, with limits $278 a month | 181st of 343, with limits $180 a month | 6th cheapest of 343 $90 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 165th of 327, with limits $5,490 a month | 126th of 327, with limits $3,600 a month | 73rd of 327, with limits $1,800 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month | 51st of 351, with limits $264 a month | 95th of 351, with limits $150 a month | 3rd cheapest of 351 $200 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
Key features
| Feature | exe.dev | Together Code Sandbox | boat |
|---|---|---|---|
| Isolation | KVM VM with Cloud Hypervisor; you cannot choose the kernel | A VM per sandbox on Together's infrastructure | Full VM with its own kernel, on physical hosts dedicated to boat (AMD Ryzen 7 9700X and Ryzen 9 9950X); vCPUs are shared |
| Getting started | Sign up for a Personal or Work plan | The SDK and CLI must be enabled for your organization by Together | Sign up with a card (7-day trial), then start a sandbox from the API, CLI or dashboard |
| Shell access | SSH, brokered through exe.dev | Commands, interactive shells and files through the SDK and CLI; SSH not documented | SSH, plus exec and files over the API |
| Docker, root and systemd | Root, systemd and Docker in every VM | Commands run as user 1000 by default, root per exec on request; Docker inside not documented | Docker, systemd and root on every sandbox |
| Nested virtualization | Off by default; available on request from support | Not documented | Yes, /dev/kvm on every sandbox |
| Images | Boot from your own Docker image in about two seconds | Build a snapshot from a Docker image or Dockerfile, then start sandboxes from it | boat's image or a saved snapshot; you cannot boot your own Docker or OCI image |
| Saving state | Disk persists and is replicated in the region; on-demand backups to your own S3 bucket, with restore (preview) | End a sandbox with a snapshot of its disk, or disk and memory; a new sandbox from a memory snapshot resumes with processes running | Disk saved every minute and at each stop; memory and running programs are not saved; kept at least 14 days when stopped |
| Fork | cp copies a VM's disk and config into a new VM | The parent stops first, then many sandboxes start from its snapshot, with memory if you ask | Fork a running sandbox from its last 1-minute snapshot; the original keeps running |
| Session length | No cap; VMs run until you stop them | Runs until you end it or its time to live ends; no idle detection or wake on request | Auto-stop defaults to 1 hour; up to 30 days, or off on a paid plan for no cap |
| Inbound traffic | HTTPS proxy for ports 3000 to 9999, one of them public; no public IP or raw TCP | A URL per port, open to everyone by default; an experimental policy limits access by IP or requires a token | Up to 50 HTTPS URLs, token-protected by default; raw ports over IPv6; no dedicated IPv4 |
| Desktop and computer use | Not built in; you can install a desktop and VNC, and Shelley's browser tool drives a headless Chromium | Not built in; you install a browser or virtual display in your own image | Built-in 60 fps desktop and Chrome, computer use, browser control |
| Coding agents | Claude Code, Codex, Pi and Shelley preinstalled; Shelley takes prompts through the API, others run through the HTTPS exec API | You install your agent in your image and run it through execs; a Harbor guide for agent evals | Seven harnesses preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Integrations inject secrets at the network edge for any HTTP host | No credentials proxy documented | Optional paid AI credentials proxy ($1 a day plus $1 per 1,000 requests) for model providers and HTTPS APIs you register |
| Regions | 9 regions in the US, Europe, Asia and Australia | Not published | Germany, Finland and France; no US or Asia region; you cannot pick one |
Every feature Battleships tracks (43)
| Feature | exe.dev | Together Code Sandbox | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Not published | Yes |
| Nested virtualization | With your own setup | No documented way | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Yes | Not published | Yes |
| Desktop GUI | No documented way | Not published | Yes |
| Browser | Yes | Not published | Yes |
| Computer-use API | No documented way | Not published | Yes |
| SSH | Yes | No documented way | Yes |
| Persistent disk | Yes | With your own setup | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | No documented way | No documented way | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | No documented way | Yes |
| Memory fork | No documented way | Yes | No documented way |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | No documented way | No documented way | No documented way |
| Wake on request | No documented way | No documented way | No documented way |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No documented way | No documented way | Yes |
| Public IPv4 | No documented way | No documented way | No documented way |
| Egress allowlist | With your own setup | No documented way | No documented way |
| Secret proxy | Yes | No documented way | Yes |
| Secret proxy for any API | Yes | No documented way | Yes |
| Preinstalled agents | Yes | No documented way | Yes |
| Agent harness API | Yes | No documented way | Yes |
| MCP server | Yes | Yes | No documented way |
| GPU | No documented way | No documented way | No documented way |
| Windows | No documented way | No documented way | No documented way |
| Arm64 | No documented way | No documented way | No documented way |
| Self-hosting | No documented way | No documented way | No documented way |
| BYOC | Yes | No documented way | No documented way |
| Open source | No documented way | No documented way | No documented way |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | Not published | Yes | Yes |
| Usage per sandbox (API) | Yes | Yes | Yes |
| Audit logs | Not published | Not published | No documented way |
| SSO | Yes | Yes | No documented way |
| SOC 2 | No documented way | Yes | No documented way |
| HIPAA | No documented way | No documented way | No documented way |
| EU data residency | Yes | Not published | No documented way |
| Zero data retention | Not published | Not published | Yes |
Performance
exe.dev and Together Code Sandbox are not in the public benchmarks we use, so we cannot say which is faster. In StarSling's run of 3 October 2026 (run 37073680030), boat did 28.06 runs/s on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, second of 15. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host; boat does not promise a CPU model.
V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. exe.dev and Together Code Sandbox are not in the public benchmarks we use, so we cannot say which is faster.
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. Start limits, per-start fees and plan minimums are in the price, boat's included.
| Scenario | exe.dev, a month | Together Code Sandbox, 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 | $35 · Personal | $5 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $35 · Personal | $22 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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 | $1,848 · Personal | $264 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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 | $530 · Personal · with limits | $900 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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 | $1,050 · Personal · with limits | $6,000 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | $8,800 · $2000/mo · with limits |
exe.dev: Personal pools are a flat monthly fee, $15 to $155 a month, for reserved vCPUs and memory that your VMs share, billed whether they are busy or idle. Standalone VMs bill per second at $0.105 per 2 vCPU / 4 GiB per hour.
Together Code Sandbox: Together lists Code Sandbox at $0.0446 per vCPU-hour and $0.0149 per GiB-hour, about $0.30 an hour at 4 vCPU / 8 GB, from prepaid credits. Billing granularity, snapshot storage and egress prices are not published. Because Code Sandbox needs enablement, the table prices Code Interpreter: $0.03 per 60-minute session.
Together Code Sandbox: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. Sandboxes bill per second while they run, busy or idle. A stopped sandbox has no compute charge; extra saved snapshots and the AI credentials proxy still charge while it is stopped.
Limits in those scenarios
The table's Together column uses Code Interpreter, so it fits none of the scenarios: sessions last 60 minutes and the machine size is not published. Code Sandbox, the VM product, goes up to 16 cores, and Together publishes no concurrency or start limits for it. exe.dev fits the single-agent and 50-agent rows, but Personal stops at 50 VMs in total, so 300 or 1,000 at once do not fit. On boat the limit that bites is starts: the $20 plan includes 200 a day and the $2,000 plan 2,400. Extra starts cost $0.03 to $0.07 each, and above 6 times the included number a start fails with 429, so 1,000 short jobs at once do not fit boat either.
| Scenario | exe.dev | Together Code Sandbox | boat |
|---|---|---|---|
| One coding agent, workdays |
|
| None for this scenario |
| One agent that never stops |
|
| None for this scenario |
| 50 agents in parallel | None for this scenario |
| None for this scenario |
| Sandboxes for your users |
|
| None for this scenario |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use exe.dev when
you want a persistent VM you reach over SSH, booted from your own Docker image, in a region near you, with SSO and roles for your team.
- A dev box you keep. For developers who want one VM to live in: SSH, root, Docker and a disk that stays, with no session cap.
- Regions around the world. Useful if your users are far from Europe: exe.dev runs in nine regions across the US, Europe, Asia and Australia.
- Team plan and an MCP server. Its Work plan covers a whole team with SSO and roles, and it serves an MCP server for controlling VMs.
Use Together Code Sandbox when
you already run models on Together and want light sandboxes, from a tenth of a core, that you can save with their memory and branch from.
- Memory snapshots to branch from. Useful for rollouts and test variants: save a sandbox with its memory and start many copies with processes still running.
- Sandboxes next to your models. Handy if you already run inference or fine-tuning on Together: sandboxes and models share one account.
- Sizes cut to the job. Good for many light jobs: sandboxes start at a tenth of a core, priced per vCPU-hour and GiB-hour.
Where boat fits
If you are choosing between exe.dev and Together because you run coding agents, look at boat too. It is a full VM you can sign up for today, like exe.dev, with the disk saved every minute and a fork of a running sandbox. It adds a built-in desktop, /dev/kvm on every sandbox, token-protected URLs and an API to drive the agents inside.
A built-in screen for your agents
Neither exe.dev nor Together has a built-in desktop. On either you build and stream a desktop yourself before an agent can check a UI. boat streams a 60 fps desktop with Chrome.
State saved every minute, and live forks
exe.dev backs up a disk only when you trigger it (preview). Together snapshots when a sandbox ends, with memory if you ask, so branching stops the parent first. boat saves the disk every minute and forks a running sandbox; it does not save memory.
Agents driven from outside, with private URLs
On exe.dev only Shelley takes prompts by API, and on Together you wire every step through execs while port URLs are public by default. boat prompts, steers and streams its preinstalled agents, and its HTTPS URLs are token-protected by default.
Use boat when your agents do real work for hours: builds, Docker, emulators, a built-in desktop and a browser, with the disk saved every minute, live forks, private URLs and one API to drive the agents inside. Compare it one to one: boat vs exe.dev and boat vs Together Code Sandbox.
boat's own limits
- Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
- Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
- A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
- Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
- boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
- Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
- Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
- Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source
Questions people ask
Is exe.dev cheaper than Together Code Sandbox?
For machines that run long, yes. At Together's Code Sandbox list rates, compute only: one agent always on costs $217 against $35 on exe.dev, and 50 agents $2,619 against $1,848. For one agent on workdays, Together costs $52 against $35. Code Sandbox must be enabled by Together, so the table uses its Code Interpreter line instead. boat costs $26, $317 and $20 for those three.
Which is faster, exe.dev or Together Code Sandbox?
We cannot say: neither is in the public benchmarks we use. In StarSling's run of 3 October 2026, boat did 28.06 V8 Web Tooling runs/s at 4 vCPU / 8 GB, on a Ryzen 9 9950X host.
Can exe.dev and Together Code Sandbox run Docker?
exe.dev VMs have root, systemd and Docker. Together builds sandboxes from Docker images, but its SDK runs commands as a normal user by default and does not document Docker inside a sandbox. boat runs Docker, systemd and root on every sandbox.
Do they have snapshots?
Yes, in different ways. exe.dev keeps each VM's disk, offers on-demand backups to your own S3 bucket (preview), and cp copies a VM. Together snapshots a sandbox's disk, or disk and memory, when it ends. boat saves the disk every minute and at each stop, without memory, and can fork a running sandbox.
Can I sign up for Together Code Sandbox today?
The together-sandbox SDK and CLI must be enabled for your organization, so you ask Together for access. exe.dev and boat both let you sign up and start a VM yourself; boat needs a card, also for the 7-day trial.
Can I run Claude Code on them?
Yes. exe.dev preinstalls Claude Code, Codex and Pi along with its Shelley agent. On Together you install your agent in your own image and run it through execs. boat preinstalls seven harnesses, with an API to prompt and steer them.
Try boat
Install the CLI, then run boat new.
7-day free trial