Together Code Sandbox vs Islo

Together Code Sandbox runs VMs from Docker-image snapshots on Together's AI cloud, but Together has to enable it for your organization, and its only self-serve product is a Python runner. Islo is a self-serve microVM for coding agents, with agents preinstalled and a gateway that controls and logs 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 it must be enabled for your organization by Together. Together also sells Code Interpreter, a separate API that runs Python code in short sessions.

Company: Together AI, a cloud for model inference, fine-tuning and GPU clusters
Isolation: A virtual machine per sandbox on Together's infrastructure
Access: The SDK and CLI must be enabled for your organization; you ask Together for access
Machine size: 0.1 to 16 cores, 1 to 8 GB of memory per core; disk size is not configurable
History: Built on CodeSandbox, now a Together company; the CodeSandbox-based SDK is deprecated and together-sandbox is its successor
Source code: The SDKs and CLI are MIT-licensed on GitHub; the platform itself is not

Islo

Islo is an agent sandbox 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. It is built for teams that run coding agents, evals and RL rollouts in the background, on Islo's cloud or in their own cloud account.

Maker: Incredibuild, a build acceleration company based in Tel Aviv
Launched: May 4, 2026
Isolation: A microVM with its own kernel for each agent computer
Regions: US West on Islo's cloud; BYOC puts the control plane and sandboxes in your own cloud account
Billing: CPU per core, memory per GB and disk per GB while a sandbox runs, billed per hour; signup credits with no card
Compliance: No certification named on its site; compliance documents on request from support

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	Islo: price rank	bochka: 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 and Together's new SDK does not document it, while bochka adds root, systemd and /dev/kvm on every machine.	65th of 367, with limits $528 a month	326th of 367, with limits $7,402 a month	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Islo fits an assistant that lives on its machine, since it can pause with memory and wake on the next request; Together has no idle detection or wake on request.	152nd of 366, with limits $1,095 a month	30th cheapest of 366 $9,928 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 Together's Code Interpreter is built for short Python runs billed per 60-minute session, while Islo and bochka run full VMs that are heavier for one-minute jobs.	326th of 345, with limits $2,190 a month	153rd of 345, with limits $503 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 300 user sandboxes at once is more than Islo's reported Team limit of 50, Together's VMs need Together to enable them, and bochka runs it on two seats.	234th of 361, with limits $900 a month	171st of 361, with limits $3,160 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 Together can save a sandbox with its memory and start many copies with processes running, which suits rollouts that branch from one warm state.	315th of 360, with limits $21,900 a month	167th of 360, with limits $15,265 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 Both document a Harbor integration for agent evals; Islo adds gateway rules that stop trials from looking up answers.	258th of 364, with limits $450 a month	198th of 364, with limits $2,456 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	251st of 377, with limits $180 a month	119th cheapest of 377 $1,507 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB	210th of 368, with limits $22 a month	112th cheapest of 368 $402 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 Together nor Islo has a desktop or computer-use API, while bochka streams a 60fps desktop with Chromium on every sandbox.	184th of 369, with limits $600 a month	310th of 369, with limits $2,210 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 Islo has a browser inside the sandbox for testing, on Together you install a headless browser in your own image, and bochka ships Chromium on a full desktop.	301st of 367, with limits $900 a month	113th of 367, with limits $1,105 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	219th of 346, with limits $180 a month	66th cheapest of 346 $748 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	124th of 338, with limits $3,600 a month	265th of 338, with limits $14,966 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	167th of 360, with limits $150 a month	47th of 360, with limits $746 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	Can't run it	Can't run it	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	Together Code Sandbox	Islo	bochka
Isolation	A VM per sandbox on Together's infrastructure	A microVM with its own kernel per sandbox	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Getting started	The SDK and CLI must be enabled for your organization by Together; only Code Interpreter is self-serve	Sign up with signup credits and no card	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	CPU, memory and disk set per sandbox	2 to 16 vCPU with 2 GB per vCPU, up to 16 vCPU / 32 GB on the $100 plan and above
Docker, root and systemd	Commands run as user 1000 by default, root on request; Docker inside not documented	Docker inside and sudo	Docker, systemd and root on every machine
Nested virtualization	Not documented	No /dev/kvm documented	Yes, /dev/kvm for Android emulators and VMs
Shell access	Commands, shells and files through the SDK and CLI; no SSH	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; new sandboxes resume with 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 on stop; a stopped sandbox costs nothing; resume boots the machine again
Fork	No live fork: the parent stops, then you start many sandboxes from its snapshot	Snapshot a running sandbox's files, then start new sandboxes from it	Fork a running sandbox; the original keeps running
Reaching the sandbox	All ports public; preview URLs coming soon; experimental inbound allowlist	HTTPS share links anyone with the URL can open, expiring after 24 hours by default; no raw TCP	HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; its own IP
Outbound internet rules	No egress allowlist documented	Gateway rules by host, path and HTTP method, default deny, with 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	Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Coding agents	Run your own agent through execs; a Harbor guide for agent evals	Claude Code, Cursor CLI and Codex preinstalled, with steer, events and triggers	Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API
Desktop and computer use	None; headless command and file access only	A browser inside for testing; no desktop or computer-use API	Linux desktop streamed at 60fps, Chromium and computer-use tools
Where it runs	Regions not published	US West, or your own cloud account with BYOC	EU only: Germany, Finland, France, with EU data residency

Every feature Battleships tracks (43)

Feature	Together Code Sandbox	Islo	bochka
Full VM (own kernel)	Yes	Yes	Yes
Docker inside	Not published	Yes	Yes
Nested virtualization	No	No	Yes
Root	Yes	Yes	Yes
Systemd	Not published	Not published	Yes
Desktop GUI	No	No	Yes
Browser	No	Yes	Yes
Computer-use API	No	No	Yes
SSH	No	Yes	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	Yes	Yes	Yes
Automatic snapshots	No	Yes	Yes
Fork/clone	Yes	Yes	Yes
Live fork (no pause)	No	Yes	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	Yes	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	Yes	Yes
Secret proxy for any API	No	Yes	Yes
Preinstalled agents	No	Yes	Yes
Agent harness API	No	Yes	Yes
MCP server	Yes	No	No
GPU	No	No	No
Windows	No	No	No
Arm64	No	No	No
Self-hosting	No	No	No
BYOC	No	Yes	No
Open source	No	No	No
Scoped API keys	Not published	Not published	Yes
Spend limits	Yes	Not published	Yes
Usage per sandbox (API)	Yes	Yes	Yes
Audit logs	Not published	Yes	No
SSO	Yes	Yes	No
SOC 2	Yes	Not published	No
HIPAA	No	Not published	No
EU data residency	Not published	No	Yes
Zero data retention	Not published	Not published	Yes

Performance

Together Code SandboxNot measured

IsloNot measured

bochka26.69 runs/s

There is no comparable CPU measurement for Together Code Sandbox or Islo: neither was part of StarSling's public sandbox benchmark run. In that run of 2026-09-29, bochka did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB on dedicated AMD Ryzen 9 9950X hosts.

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 Islo 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	Islo, a month	bochka, 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	$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 prices Code Interpreter: $0.03 per 60-minute session from prepaid credits. Code Interpreter runs only Python and keeps no disk, so it does not fit these scenarios.

Islo: Islo bills each CPU core and each GB of memory and disk while a sandbox runs, per hour, with no plan fee. An idle sandbox keeps billing until a pause-after-idle timer set at creation fires, and egress has no published price.

Islo: Plans start at $20 a month, and the whole fee becomes usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

The Together column is Code Interpreter, and its limits decide every row: sessions last 60 minutes, nothing is kept after a session, it runs only Python and the machine size is not published. Islo fits the first three scenarios, but its Team plan is reported at 50 running sandboxes at once, so 300 sandboxes for your users and 1,000 short jobs at once need a custom contract. On bochka the limit that bites is starts: the 1,000-job burst needs more starts per hour and per day than even the $2,000 plan allows, so starts are queued.

Scenario	Together Code Sandbox	Islo	bochka
One coding agent, workdays	Together pay-as-you-go (prepaid credits; Code Interpreter only): sessions capped at 1 h missing persistent disk machine size not published different kind of product: code interpreter	egress price not published	None that bite
One agent that never stops	Together pay-as-you-go (prepaid credits; Code Interpreter only): sessions capped at 1 h missing persistent disk machine size not published different kind of product: code interpreter	egress price not published	None that bite
50 agents in parallel	Together pay-as-you-go (prepaid credits; Code Interpreter only): sessions capped at 1 h missing persistent disk, Docker inside machine size not published different kind of product: code interpreter	egress price not published	None that bite
Sandboxes for your users	machine size not published different kind of product: code interpreter machine size per session not published egress price not published	Team: max 50 concurrent egress price not published	None that bite
1,000 short jobs at once	machine size not published different kind of product: code interpreter machine size per session not published egress price not published	Team: max 50 concurrent egress price not published	max 2,400 starts/day (needs ~6,667) max 600 starts/hour (needs ~1,000) bursts above 90 starts/min are queued (a burst of 333 takes ~4 min to start)

Which one should you use?

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, or a simple Python runner billed per session.

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 and API key.
Very small machines and a Python runner. Good for many light jobs: sandboxes start at a tenth of a core, and a Python interpreter API bills per session.

Use Islo when

you want self-serve agent microVMs today, with per-host egress rules and a log of every outbound call, sandboxes that pause with memory and wake on request, or a US region or your own cloud account.

Self-serve agent sandboxes. Good if you want to start today: sign up with free credits 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 bochka fits

If your agents need more than a shell, look at bochka. Every sandbox is a full VM you can sign up for today, with root, systemd, Docker, /dev/kvm, a 60fps desktop, coding agents preinstalled and ports you can host on. Neither Together nor Islo has a desktop or nested virtualization, and both make hosting a preview harder.

A desktop agents can see and use

Neither Together nor Islo has a screen or a computer-use API, so an agent that checks a UI or fills a form in a real app needs a VNC stack and a control layer you build into each image. bochka streams a 60fps desktop with Chromium.

Nested virtualization and systemd

Android emulators and tools that start their own VMs stop at the first boot without /dev/kvm, and neither Together nor Islo documents it. On Together, Docker inside is not documented either. bochka has Docker, systemd and /dev/kvm on every machine.

Ports you can host on

On Together every port is public and preview URLs are not out yet; Islo share links are open to anyone with the URL and expire after 24 hours by default. bochka serves 50 HTTPS ports with token protection, plus raw TCP.

Use bochka when your agents need a whole machine: Docker, /dev/kvm for emulators, a desktop for computer use, ports you can host on and up to 2,000 sandboxes at once, in the EU. Compare it one to one: bochka vs Together Code Sandbox and bochka vs Islo.

Questions people ask

Is Together Code Sandbox cheaper than Islo?

Together's only self-serve price is Code Interpreter, which does not fit these scenarios because sessions end after 60 minutes and keep no disk. Islo fits one coding agent on workdays at $101 a month and 50 agents in parallel at $4,863 a month. bochka comes to $20 and $317 a month for the same two.

Which is faster, Together Code Sandbox or Islo?

There is no public CPU measurement for either. bochka did 26.69 runs per second on StarSling's Node.js test at 4 vCPU / 8 GB, and neither Together nor Islo was part of that run.

Can Together Code Sandbox or Islo run Docker?

Islo runs Docker inside its microVMs, with sudo. Together builds sandboxes from Docker images, but its new SDK does not document Docker inside a sandbox, and commands run as a normal user unless you ask for root. bochka runs Docker, systemd and root on every machine.

Can I start using them today?

Islo is self-serve, with signup credits and no card. Together's VM sandboxes must be enabled for your organization by Together, so only the Python Code Interpreter is self-serve. bochka is self-serve from the API, CLI or dashboard.

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. bochka saves the disk every minute and on stop, and a resumed sandbox boots again.

Is bochka SOC 2 compliant?

SOC 2 is in progress. We're open about where we stand: live status at status.bochka.xyz and our data retention policy at docs.bochka.xyz/data-retention.

Try bochka

Install the CLI, then run bochka new.

Product preview