Blaxel vs Islo
Both give every agent a microVM with its own kernel and can pause it with its memory kept. Blaxel is built to sleep in seconds and wake in under 25 ms, while Islo is built around a gateway that checks, fills credentials into and logs every outbound request.
The companies and products
Blaxel
Blaxel is a San Francisco company that runs cloud infrastructure for AI agents, and since September 2026 it is part of Baseten.
You get sandboxes, batch jobs, MCP server hosting and a model gateway. Each sandbox is a Firecracker microVM with its own kernel that drops to standby when nothing is connected and resumes in under 25 ms with its memory and running processes. It is built for agent products that start many sandboxes and want them asleep most of the time.
- Headquarters
- San Francisco, founded 2024
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.
- 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. “10th cheapest of 367” means 9 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 | Blaxel: 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 Blaxel fits a software factory and Islo is a compromise there; neither has /dev/kvm, so Android emulators need boat. | 10th cheapest of 367 $2,373 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 Both fit mostly idle assistants: Blaxel sleeps seconds after the last connection, and Islo pauses after an idle timer you set at creation. | 12th cheapest of 366 $2,832 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 Blaxel is the better pick for short bursts, since it sleeps right away and resumes in milliseconds, while Islo's Team plan stops at 50 running at once. | 14th cheapest of 345 $144 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 users at once is past Blaxel's 200 on Tier 2 and Islo's 50 on Team, so both need a sales deal, while boat fits it on a self-serve plan. | 101st of 361, with limits $926 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 | 77th of 360, with limits $4,378 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 Islo has a built-in Harbor integration and gateway rules that stop trials from looking up answers; boat starts a fresh VM per task and runs more at once. | 136th of 364, with limits $704 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 | 57th cheapest of 377 $431 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 Islo gives you SSH through its CLI and no lifetime limit, while Blaxel has no native SSH and deletes sandboxes after 7 or 30 days on its lower tiers. | 265th of 368, with limits $114 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 Blaxel runs a desktop and a browser, Islo sandboxes are headless with no computer-use API, and boat streams a 60fps desktop you can embed. | 14th cheapest of 369 $634 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 | 16th cheapest of 367 $317 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 | 16th cheapest of 346 $215 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 | 147th of 338, with limits $4,292 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 Both can lock egress by domain, method and path; Islo adds per-request logs, and boat gives root with raw TCP. | 3rd cheapest of 360 $217 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 | Blaxel | Islo | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | MicroVM with its own kernel, built from a container image | Full VM with its own kernel, on dedicated AMD Ryzen 9 9950X hosts |
| Nested virtualization | No: Firecracker guests do not get /dev/kvm | No /dev/kvm or nested virtualization documented | Yes: /dev/kvm, so Android emulators and VMs run inside |
| Pause and wake | Standby a few seconds after the last connection; wakes in under 25 ms with memory and processes | Pause keeps files, processes and memory; pause after idle must be set at creation; resumes on exec, file access or webhook | Stop keeps the disk and costs nothing; resume boots the VM again |
| Disk | Files live in memory (about half the RAM); one volume can be attached at creation | Disk billed per GB while the sandbox runs | A real disk that stays, snapshotted every minute and on stop |
| Fork | Fork with memory and running processes (private preview) | Snapshot a running sandbox's files, then start new sandboxes from it | Fork a running sandbox into new ones |
| Shell access | Root, terminal through bl connect, no native SSH | Sudo, SSH and port-forward through the Islo CLI | Real SSH, root and systemd |
| Desktop and computer use | Desktop and browser control | A browser for testing; no desktop or computer-use API | 60fps desktop with Chromium, computer-use API, embeddable stream |
| Inbound traffic | Preview URL per port, public or token-protected; no raw TCP or public IP | 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 |
| Outbound rules | Domain allow and deny lists, method and path rules, static egress IPs | Allow or deny by host, path and method, default deny, rate limits, content filters | Open internet; filter inside the VM with nftables |
| Request logs | Per-sandbox cost and usage API | Per-request gateway logs of every call and block, streamed to your SIEM | Usage API and spend limits; no per-request log of outbound calls |
| Keeping keys out | Proxy fills secrets into outbound HTTPS requests (public preview) | Gateway fills stored credentials into outbound requests for any host | AI credentials proxy for model providers and any HTTPS API you register |
| Coding agents | Claude Code image you drive from its terminal or your own harness | Claude Code, Cursor CLI and Codex preinstalled; factory lines with events, steer and triggers | Claude Code, Codex, OpenCode and more, driven by a prompt, steer and events API |
| Sandboxes at once | 10, 50 or 200 by self-serve tier; standby sandboxes count | Free 5, Team 50 running; paused ones do not count | 100 to 2,000 running by plan |
| Regions | Oregon, North Virginia, London, Frankfurt | US West, or your own cloud account with BYOC | EU only: Germany, Finland, France, with EU data residency |
Every feature Battleships tracks (43)
| Feature | Blaxel | Islo | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | No | Not published | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | Yes | No | Yes |
| SSH | No | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | Yes | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | Yes | 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 | Yes | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Yes | No |
| Secret proxy | Yes | Yes | Yes |
| Secret proxy for any API | Yes | Yes | Yes |
| Preinstalled agents | Yes | 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 | Yes | Yes | No |
| Open source | No | No | No |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | No | 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 | Yes | Not published | No |
| EU data residency | Yes | No | Yes |
| Zero data retention | Yes | Not published | Yes |
Performance
In StarSling's benchmark run of 2026-09-29, at 4 vCPU and 8 GB, boat did 26.69 Node.js build-and-test runs per second and Blaxel 19.48, so boat does about 1.4 times the work in the same time. Islo has no comparable measurement: it was not part of that run or the other public results we use. Higher is better.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Blaxel measured on: Sandbox (active time, RAM-only pricing, CPU bundled). Islo has 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 | Blaxel, 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 | $33 · Pay-as-you-go Tier 1 | $101 · Free | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $120 · Pay-as-you-go Tier 1 | $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 | $1,489 · Pay-as-you-go Tier 1 | $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 | $396 · Pay-as-you-go Tier 2 · 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 | $876 · Pay-as-you-go Tier 2 · with limits | $3,053 · Team · with limits | $2,000 · $2000/mo · with limits |
Blaxel: Blaxel charges for allocated RAM per second while a sandbox is active, with CPU included (8 GB comes with 4 cores). In standby you pay only snapshot storage, and volumes are billed on their full size.
Islo: Islo bills each CPU core and each GB of memory and disk while a sandbox runs, billed per hour, with no plan fee. An idle sandbox keeps billing until its pause timer fires, and egress has no published price.
Islo: You pick a monthly plan from $20, and all of it becomes usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
Blaxel's self-serve tiers allow 10, 50 or 200 sandboxes at once, and sandboxes in standby count toward that. Islo's Team plan is reported at 50 running sandboxes, with paused ones left out. So 300 sandboxes for your users and 1,000 short jobs at once fit neither without a sales deal, and boat queues the 1,000-job burst because it limits starts per minute. Islo publishes no egress price, so its totals here leave egress out.
| Scenario | Blaxel | Islo | boat |
|---|---|---|---|
| One coding agent, workdays | None that bite |
| None that bite |
| One agent that never stops | None that bite |
| None that bite |
| 50 agents in parallel | None that bite |
| None that bite |
| Sandboxes for your users |
|
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Blaxel when
your sandboxes sit idle most of the time and must wake in milliseconds with their memory, or you want US and UK regions with a measured CPU.
- Wakes in milliseconds. For sandboxes that sit idle most of the time: Blaxel sleeps seconds after the last connection and wakes in under 25 ms.
- A published CPU score. Blaxel did 19.48 Node.js build-and-test runs per second at 4 vCPU and 8 GB; Islo has no public score to compare.
- US and Europe regions. For teams with users on both sides of the Atlantic: Blaxel runs in Oregon, North Virginia, London and Frankfurt.
Use Islo when
you must control and log every outbound call an agent makes, want agent pipelines on triggers, or need to run in your own cloud account.
- Every outbound call logged. For teams that must show what agents reached: Islo logs each request and each block, and streams it to your SIEM.
- A real disk and no forced expiry. For long-lived agents: Islo keeps files on disk with no lifetime ceiling, while Blaxel's lower tiers delete sandboxes after 7 or 30 days.
- Agent pipelines built in. Islo ships Claude Code, Cursor CLI and Codex, and runs agent steps on a schedule, a webhook or GitHub, Slack and Linear events.
Where boat fits
Blaxel and Islo are both built around agents that sleep between short steps. If your agents work for hours on builds, tests, Docker, emulators or a desktop, boat gives each one a whole Linux machine with a real disk and a faster CPU, and runs up to 2,000 at once.
A whole machine with /dev/kvm
Neither Blaxel nor Islo exposes /dev/kvm, so an Android emulator or a VM inside the sandbox does not start. boat gives root, systemd, Docker and /dev/kvm on every sandbox.
A faster CPU, measured
At 4 vCPU and 8 GB, boat did 26.69 runs per second and Blaxel 19.48, so every install, build and test waits about 1.4 times as long on Blaxel. Islo has no public score at all.
A desktop and ports you can host on
Islo is headless and its share links are open to anyone and expire after 24 hours; Blaxel has no raw TCP. boat streams a 60fps desktop and serves 50 token-protected ports plus raw TCP.
Use boat when your agents do real work for hours: builds, tests, Docker, emulators and a desktop on a whole Linux machine with a real disk, a faster CPU and up to 2,000 sandboxes at once. Compare it one to one: boat vs Blaxel and boat vs Islo.
Questions people ask
Is Blaxel cheaper than Islo?
In every scenario we priced, yes: one coding agent on workdays is $33 a month on Blaxel and $101 on Islo, and 50 agents in parallel are $1,489 against $4,863. boat comes to $20 and $317 for the same two. Blaxel only bills while a connection is open, so a workload that disconnects often pays less.
Which is faster, Blaxel or Islo?
We cannot say: Blaxel did 19.48 runs per second on StarSling's Node.js benchmark, but Islo has no public score. boat did 26.69 on the same benchmark.
Can Blaxel and Islo run Docker?
Yes, both run Docker inside: Blaxel with its Docker-in-sandbox image, Islo inside its microVMs. Neither documents /dev/kvm, so Android emulators and nested VMs need boat.
Do Blaxel and Islo keep memory when a sandbox sleeps?
Both do. Blaxel goes to standby seconds after the last connection and wakes in under 25 ms; Islo pauses after an idle timer you set at creation and resumes on the next exec, file access or webhook. boat keeps the disk and reboots on resume.
Can I SSH into Blaxel or Islo?
Islo gives SSH and port-forwarding through its CLI. Blaxel has no native SSH and gives a terminal through bl connect. boat sandboxes take real SSH.
Who makes Blaxel and Islo?
Blaxel is a San Francisco company that joined Baseten on September 10, 2026, with the product unchanged. Islo is made by Incredibuild, a build acceleration company in Tel Aviv, and launched on May 4, 2026.
Try boat
Install the CLI, then run boat new.
7-day free trial