Together Code Sandbox vs Islo
Together Code Sandbox runs VMs from Docker-image snapshots on Together's AI cloud and can save their memory when they end. Together must enable it for your organization. Islo is a self-serve microVM for coding agents, with agents preinstalled and a gateway that can control and log every outbound call.
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 Together must enable it for your organization. The pricing page also lists Code Interpreter at $0.03 per 60-minute session.
Islo
Islo is an agent sandbox and coding-agent factory from Incredibuild: each coding agent gets its own microVM, with network rules and credentials handled at a gateway.
An Islo sandbox is a Linux microVM with its own kernel, built from a container image, with Claude Code, Cursor CLI and Codex preinstalled. Outbound traffic can pass through a gateway that allows or blocks hosts, injects credentials and logs every request. Islo also runs factory lines: saved agents run steps on a schedule, on a webhook or on GitHub, Slack, Linear and Jira events. It runs on Islo's cloud or in your own cloud account.
- Launched
- May 4, 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. “67th cheapest of 365” means 66 of the other 364 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 | Islo: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Islo runs Docker inside its microVMs. Together does not document Docker inside a sandbox. boat runs Docker with systemd, root and /dev/kvm on every sandbox. | 67th of 365, with limits $528 a month | 60th of 365, with limits $7,402 a month | 5th cheapest of 365 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Islo fits an assistant that waits between tasks: it can pause with its memory after idle time and wake on the next request. A Together sandbox runs until you end it or its time to live ends, with no idle detection. boat keeps a sandbox running with auto-stop off (default 1 hour), billed at full rate while it runs. | 107th of 361, with limits $1,095 a month | 37th cheapest of 361 $9,928 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 Both run short code through an API. Together's pricing page also lists Code Interpreter at $0.03 per 60-minute session. Islo bills CPU, memory and disk per hour while a sandbox runs. On boat, each create counts as a start against the plan's start limits. | 318th of 336, with limits $2,190 a month | 155th of 336, with limits $503 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 For 300 user sandboxes at once, Islo publishes no concurrency limit, and launch coverage reported 50 on its Team plan, so ask Islo first. On Together every port URL is public unless you set an experimental access policy. boat fits this scenario at $200 a month on the $100 plan with 2 seats. | 231st of 349, with limits $900 a month | 172nd of 349, with limits $3,160 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. boat forks a running sandbox from its last 1-minute disk snapshot, without memory, and caps starts per plan. | 309th of 349, with limits $21,900 a month | 174th of 349, with limits $15,265 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 Both document a Harbor integration for agent evals. Islo adds gateway rules that can stop trials from looking up answers. boat has a Harbor integration too, with no provider-side egress rules. | 260th of 359, with limits $450 a month | 203rd of 359, with limits $2,456 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 | 253rd of 374, with limits $180 a month | 124th cheapest of 374 $1,507 a month | 2nd cheapest of 374 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 226th of 371, with limits $22 a month | 117th cheapest of 371 $402 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 ships a desktop. On Islo a setup script can install Xvfb and a VNC server; on Together you build them into your image. boat streams a 60fps desktop with Chrome and computer-use tools. | 105th of 367, with limits $600 a month | 63rd cheapest of 367 $2,210 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 Islo has a browser-use capability inside the sandbox. On Together you install a browser in your own image. boat ships Chrome on a full desktop in every sandbox. | 195th of 356, with limits $900 a month | 151st of 356, with limits $1,105 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 | 181st of 343, with limits $180 a month | 71st cheapest of 343 $748 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 | 126th of 327, with limits $3,600 a month | 266th of 327, with limits $14,966 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 | 95th of 351, with limits $150 a month | 78th of 351, with limits $746 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 | Together Code Sandbox | Islo | boat |
|---|---|---|---|
| Isolation | A VM per sandbox on Together's infrastructure | A microVM with its own kernel per sandbox | 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 | The SDK and CLI must be enabled for your organization by Together | Sign up with signup credits and no card | Sign up with a card (7-day trial), then 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 not configurable | CPU, memory and disk set per sandbox | 2, 4, 8 or 16 vCPU at 2 GB per vCPU; disk fixed per size, 51 to 251 GB; 16 vCPU needs the $100 plan or higher |
| Docker and root | Commands run as user 1000 by default, root per exec on request; Docker inside a sandbox is not documented | Docker inside, with sudo | Docker with Compose, systemd and root on every sandbox |
| Nested virtualization | Not documented | No /dev/kvm documented | Yes, /dev/kvm for Android emulators and VMs |
| Shell access | Commands, interactive shells and files through the SDK and CLI; SSH is not documented | SSH and port-forward through the CLI | SSH, plus exec and files over the API |
| Saving state | End a sandbox with a snapshot of its disk, or disk and memory; a new sandbox from a memory snapshot resumes with its processes running | Pause keeps files, processes and memory; can pause after idle time and wake on the next exec, file access or webhook | Disk saved every minute and at each stop; memory and running programs are not saved, so a resume is like a reboot |
| Fork | The parent stops first, then you start many sandboxes from its snapshot, with memory if you ask | Snapshot a running sandbox's files, then start new sandboxes from it | Fork a running sandbox from its last 1-minute disk snapshot; the original keeps running; memory is not copied |
| Reaching the sandbox | A URL per port, open to everyone by default; an experimental policy limits access by IP or requires a token | HTTPS share links that anyone with the URL can open, expiring after a TTL (24 hours by default); SSH and port-forward through the CLI | Up to 50 HTTPS URLs per sandbox, token-gated by default; SSH; raw ports (IPv6 only on sandboxes with no IPv4 of their own) |
| Outbound internet rules | No egress allowlist documented | Open by default; optional gateway profiles allow or deny by host, path and HTTP method, with default deny and per-request logs | Open internet; no provider-side allowlist |
| Keeping API keys out of the sandbox | No credentials proxy documented | Gateway injects stored credentials into outbound requests for any host | Optional AI credentials proxy ($1 a day plus $1 per 1,000 requests) for model providers and HTTPS APIs you register; other secrets still enter the sandbox |
| Coding agents | You install your agent in your image and run it through execs; a Harbor guide for agent evals | Claude Code, Cursor CLI and Codex preinstalled; factory lines run agent steps on a schedule, a webhook or GitHub, Slack, Linear and Jira events | Seven harnesses preinstalled, including Claude Code, Codex and OpenCode, with a prompt, steer and events API |
| Desktop and computer use | No built-in desktop or stream; install a browser or virtual display in your own image | Browser-use capability built in; no desktop or computer-use API. You set it up: install Xvfb and a VNC server with a setup script | Linux desktop and Chrome streamed at 1920x1080, 60fps, with computer-use tools |
| Where it runs | Regions not published | Islo's cloud (regions not published, set per account), or your own cloud account with BYOC | Germany, Finland and France; you cannot pick a region; no US or Asia region |
Every feature Battleships tracks (43)
| Feature | Together Code Sandbox | Islo | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Not published | Yes | Yes |
| Nested virtualization | No documented way | No documented way | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | Not published | With your own setup | Yes |
| Browser | Not published | Yes | Yes |
| Computer-use API | Not published | No documented way | Yes |
| SSH | No documented way | Yes | Yes |
| Persistent disk | With your own setup | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | No documented way | Yes | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | No documented way | Yes | Yes |
| Memory fork | Yes | No documented way | No documented way |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | No documented way | Yes | No documented way |
| Wake on request | No documented way | Yes | 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 | No documented way | Yes | No documented way |
| Secret proxy | No documented way | Yes | Yes |
| Secret proxy for any API | No documented way | Yes | Yes |
| Preinstalled agents | No documented way | Yes | Yes |
| Agent harness API | No documented way | Yes | Yes |
| MCP server | Yes | No documented way | 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 | No documented way | Yes | No documented way |
| Open source | No documented way | No documented way | No documented way |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Yes | Yes | Yes |
| Usage per sandbox (API) | Yes | Yes | Yes |
| Audit logs | Not published | Yes | No documented way |
| SSO | Yes | Yes | No documented way |
| SOC 2 | Yes | Not published | No documented way |
| HIPAA | No documented way | Not published | No documented way |
| EU data residency | Not published | No documented way | No documented way |
| Zero data retention | Not published | Not published | Yes |
Performance
Together Code Sandbox and Islo 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 also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure.
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. Together Code Sandbox and Islo 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 | Together Code Sandbox, a month | Islo, 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 | $101 · Free | $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 | $420 · Free | $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 | $4,863 · 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 | $900 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | $1,382 · Team · 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 | $6,000 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | $3,053 · Team · with limits | $8,800 · $2000/mo · with limits |
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, once Together enables it for your organization. Billing granularity, snapshot storage and egress prices are not published. The pricing page also lists Code Interpreter at $0.03 per 60-minute session; the scenario tables use that line because Code Sandbox needs enablement.
Islo: Islo has no plan fee. It bills $0.07 per CPU-hour, $0.04 per GB-hour of memory and $0.0007 per GB-hour of disk for what you give a sandbox while it runs. A paused or stopped sandbox has no compute charge. A running idle sandbox bills at full rate until a pause-after-idle timer fires, and that timer can only be set when the sandbox is created. Billing granularity and egress prices are not published.
Islo: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. A running sandbox bills per second at full rate, busy or idle: $0.036 an hour for 4 vCPU / 8 GB. A stopped sandbox has no compute charge and keeps its disk for at least 14 days. Saved snapshots above the included count and the optional AI credentials proxy still charge while sandboxes are stopped. The $20 plan includes 12 starts a minute and 200 a day; extra starts cost $0.03 to $0.07. A card is required, also for the 7-day trial.
Limits in those scenarios
The tables price Together with the Code Interpreter line on its pricing page ($0.03 per 60-minute session), because Code Sandbox needs Together to enable it. Those sessions last 60 minutes and their machine size is not published, so that line fits none of the scenarios. Code Sandbox, the VM product, goes up to 16 cores, and Together publishes no concurrency or start limits for it. Islo fits the first three scenarios. Its pricing page names no concurrency limit, and launch coverage in May 2026 reported 50 running sandboxes on Team, so the tables treat 300 user sandboxes and 1,000 jobs at once as needing a higher limit from Islo. Islo publishes no egress price, so its totals leave egress out. On boat the limit that bites is starts: the $20 plan includes 12 a minute, 60 an hour and 200 a day, and the $2,000 plan 90 a minute and 2,400 a day. Extra starts cost $0.03 to $0.07, and starts above 3 times the included rate per minute fail with 429. boat never queues a start, so the 1,000-job burst does not fit boat as listed and costs about $8,800 a month with paid starts.
| Scenario | Together Code Sandbox | Islo | 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 |
| Sandboxes for your users |
|
| None for this scenario |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Together Code Sandbox when
you already run models on Together, can get the VMs enabled, and want light sandboxes, from a tenth of a core, that you 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.
Use Islo when
you want self-serve agent microVMs today, per-host egress rules with a log of every outbound call, credentials injected for any host, sandboxes that pause with memory and wake on request, or your own cloud account.
- Self-serve agent sandboxes. Good if you want to start today: sign up with signup credits and no card, and get microVMs with coding agents preinstalled.
- Egress rules and request logs. Useful if you must control what agents reach: Islo allows or blocks each host, path and method, and logs every call.
- Pause with memory, wake on request. Useful for agents that sit idle between tasks: Islo pauses them with memory kept and resumes on the next request.
Where boat fits
Look at boat if your agents need more than a shell. Every sandbox is a full VM with root, systemd, Docker, /dev/kvm, a 60fps desktop, seven coding agents and up to 50 token-protected HTTPS URLs. boat needs a card, has no region choice and caps starts per plan.
A desktop agents can see and use
Neither Together nor Islo ships a screen or a computer-use API. On Islo a setup script can install Xvfb and a VNC server, and on Together you build them into your image; your own tooling then drives them. boat streams a 60fps desktop with Chrome and computer-use tools.
Nested virtualization and systemd
Android emulators and tools that start their own VMs need /dev/kvm, and neither Together nor Islo documents it. Together does not document Docker inside a sandbox either. boat has Docker, systemd and /dev/kvm on every sandbox. boat has no GPU on any size.
Ports you can host on
Together port URLs are open to everyone unless you set an experimental policy. Islo share links are open to anyone with the URL and expire after 24 hours by default. boat serves up to 50 HTTPS ports with token protection by default. Raw ports on sandboxes with no IPv4 of their own work over IPv6 only.
Use boat when your agents need a whole machine: Docker, /dev/kvm for emulators, a built-in desktop for computer use, ports you can host on, and up to 2,000 sandboxes at once on the $2,000 plan, within its start limits. Compare it one to one: boat vs Together Code Sandbox and boat vs Islo.
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 Together Code Sandbox cheaper than Islo?
It depends on the line you compare. The tables price Together with Code Interpreter, which fits none of these scenarios because its sessions last 60 minutes. Code Sandbox itself lists about $0.30 an hour at 4 vCPU / 8 GB. Islo fits one coding agent on workdays at $101 a month, one agent 24/7 at $420 and 50 agents in parallel at $4,863. boat comes to $20, $26 and $317 for the same three. Below about $20 of use a month, Islo costs less, because boat's smallest plan is $20. Islo totals leave out egress.
Which is faster, Together Code Sandbox or Islo?
Neither is in the public benchmarks we use, so we cannot say. In StarSling's run of 3 October 2026, boat did 28.06 runs/s on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, second of 15, on an AMD Ryzen 9 9950X host. boat does not promise a CPU model.
Can Together Code Sandbox or Islo run Docker?
Islo runs Docker inside its microVMs, with sudo. Together builds sandboxes from Docker images, but its SDK does not document Docker inside a sandbox, and commands run as a normal user unless you ask for root per exec. boat runs Docker, systemd and root on every sandbox, plus /dev/kvm.
Can I start using them today?
Islo is self-serve, with signup credits and no card. Together's SDK and CLI must be enabled for your organization, so you ask Together for access. boat is self-serve with a card, and the 7-day trial needs a card too.
Do they keep memory when a sandbox stops?
Both can. Together saves disk and memory as a snapshot when a sandbox ends, and new sandboxes start from it with processes running. Islo pauses a sandbox with its memory and wakes it on the next request. boat saves the disk every minute and at each stop, not memory, so a resume is like a reboot. A stopped boat sandbox keeps its disk for at least 14 days.
Is boat SOC 2 compliant?
SOC 2 is in progress at boat, so there is no SOC 2 report today. Together's trust center lists a SOC 2 Type 2 report. Islo names no certification on its site and sends compliance documents on request. boat's live status is at status.ascii.dev and its 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 Islo
- 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