bochka vs Beam
Both give an agent a Linux machine you drive from code. bochka gives every sandbox a full VM with /dev/kvm, agents and a desktop built in, while Beam is a serverless GPU platform with fast gVisor sandboxes and a separate line of persistent CPU VMs.
Where bochka stands out
A full VM, not a container
Each bochka sandbox is a full VM with its own kernel, root, systemd and Docker, on dedicated AMD Ryzen 9 9950X hosts. It also exposes /dev/kvm, so Android emulators and VMs run inside it. A Beam sandbox is a gVisor container by default, and Beam VMs, while microVMs with their own kernel, document no /dev/kvm.
Hosting with access control
bochka serves HTTPS on up to 50 ports per sandbox, token-protected by default, plus raw TCP and a dedicated IPv4 or IPv6. A Beam sandbox gives each exposed port a public HTTPS URL with no built-in auth, and neither Beam sandboxes nor Beam VMs offer raw TCP or a dedicated IP.
Agents, desktop and keys built in
Claude Code, Codex and five other agents come preinstalled, and you prompt, steer and follow them through one API. Each sandbox has a 60fps desktop with Chromium for computer use. Real API keys stay outside the sandbox in a credentials proxy.
The companies and products
bochka
bochka.xyz runs sandboxes for AI agents: each one is a full Linux VM with its own kernel.
You start a machine with one command or one API call, then SSH in, run Docker, open a desktop, or let a built-in agent (Claude Code, Codex, OpenCode and others) work in it. The disk stays between sessions, and a stopped sandbox costs nothing.
- Isolation
- Full VM per sandbox, own kernel
- Regions
- EU: Germany, Finland, France
Beam
Beam is a serverless cloud for GPU inference, sandboxes and background jobs, built on its open-source runtime Beta9.
Beam runs functions, REST endpoints, task queues, pods, sandboxes and VMs on CPUs and GPUs, all from a Python or TypeScript SDK. A sandbox is a container isolated with gVisor that starts in a second or two, lives until you terminate it or its time to live runs out, and can be saved as a filesystem image or a memory snapshot. Beam VMs are a separate CPU product: a microVM with its own kernel, systemd and a root disk that stays when it stops. Much of Beam is a GPU serverless platform for AI teams.
- Bring your own cloud
- Management fee per vCPU and GB of RAM, on top of your own cloud bill
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. “3rd cheapest of 367” means 2 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 | bochka: price rank | Beam: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory needs Docker, systemd, /dev/kvm and a disk that survives between runs, which bochka gives every sandbox; Beam sandboxes end with their time to live, and Beam VMs document no /dev/kvm. | 3rd cheapest of 367 $634 a month | 69th of 367, with limits $551 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that lives on its machine all month fits a bochka sandbox or a Beam VM, both of which keep their disk while stopped; bochka adds the agents, desktop and credentials proxy. | 5th cheapest of 366 $657 a month | 115th of 366, with limits $651 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Beam fits this well: sandboxes start in a second or two, bill per second and go away on their own when the timer ends. | 186th of 345, with limits $2,000 a month | 8th cheapest of 345 $117 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month Both fit; bochka gives each user a full VM with hosting and a disk that persists, while Beam gives each one a quick container. | Cheapest of 361 $209 a month | 3rd cheapest of 361 $290 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month | 34th of 360, with limits $2,000 a month | 341st of 360, with limits $939 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month | 10th cheapest of 364 $200 a month | 13th cheapest of 364 $251 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI jobs that build Android apps or VM images need /dev/kvm, which a bochka sandbox has and a gVisor container does not. | 4th cheapest of 377 $86 a month | 12th cheapest of 377 $171 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Both keep your work when the machine stops: bochka saves the disk every minute and on stop, and a Beam VM keeps its 50 GiB root disk. | 18th cheapest of 368 $26 a month | 13th cheapest of 368 $21 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month bochka ships a Linux desktop streamed at 60fps with Chromium for computer use; Beam has no browser or computer-use product, so you would build that yourself. | 6th cheapest of 369 $200 a month | 111th of 369, with limits $237 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month | 7th cheapest of 367 $200 a month | 195th of 367, with limits $176 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 6th cheapest of 346 $90 a month | 200th of 346, with limits $131 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 71st of 338, with limits $1,800 a month | 42nd of 338, with limits $923 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month | 2nd cheapest of 360 $200 a month | 175th of 360, with limits $155 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month Beam has GPUs, from RTX 4090 to H100 and B200; bochka is CPU only. | Can't run it | Cheapest of 98 $458 a month |
| 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 |
Key features
| Feature | bochka | Beam |
|---|---|---|
| Isolation | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts | gVisor container by default for sandboxes; separate Beam VMs are CPU microVMs with their own kernel |
| Nested virtualization | Yes, /dev/kvm for Android emulators and VMs | Not documented |
| Docker and systemd | Docker, systemd and root, like a normal Ubuntu server | Docker inside sandboxes with docker_enabled; systemd only in Beam VMs, not in sandboxes |
| Lifetime | No session cap on paid plans; you set the time to live | Default 10 minutes; set -1 to run until you terminate it |
| Disk between runs | Disk is saved every minute and on stop, and a stopped sandbox keeps it for free | A sandbox ends with its time to live unless you save an image or use a volume; a Beam VM keeps a 50 GiB root disk while stopped |
| Fork and snapshots | Fork a running sandbox with its disk | Memory snapshot of a running sandbox with its processes, restored into new sandboxes |
| GPUs | No, CPU only | GPU sandboxes and serverless GPUs up to H100, H200 and B200 |
| Desktop and browser | Linux desktop streamed at 60fps with Chromium and computer use | No desktop or browser product |
| Inbound access | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6 | HTTPS only: a sandbox URL per exposed port is public with no built-in auth; no raw TCP or dedicated IP on sandboxes or VMs |
| Outbound rules | Open internet, no provider-side allowlist | Block all outbound traffic, or allow up to 10 CIDR ranges, changeable while running |
| Coding agents | Seven agents preinstalled, with a prompt, steer and events API | None preinstalled; you install and run them through process exec |
| Keeping API keys out of the sandbox | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out | Secrets are exposed as environment variables inside the sandbox |
| Regions | EU only (Germany, Finland, France) | US only; no other region is listed |
| Self-hosting | No | Beta9 runtime is AGPL-3.0 and free to self-host; bring your own cloud for a fee |
| Compliance and transparency | SOC 2 is in progress. We're open about where we stand: live status and data retention policy. | SOC 2 |
Every feature Battleships tracks (43)
| Feature | bochka | Beam |
|---|---|---|
| Full VM (own kernel) | Yes | No |
| Docker inside | Yes | Yes |
| Nested virtualization | Yes | No |
| Root | Yes | Yes |
| Systemd | Yes | No |
| Desktop GUI | Yes | No |
| Browser | Yes | No |
| Computer-use API | Yes | No |
| SSH | Yes | Yes |
| Persistent disk | Yes | Yes |
| Pause/resume | Yes | No |
| Automatic snapshots | Yes | No |
| Fork/clone | Yes | Yes |
| Live fork (no pause) | Yes | Yes |
| Memory fork | No | Yes |
| Custom image (Docker or snapshot) | Yes | Yes |
| ≥24 h sessions | Yes | Yes |
| Idle auto-stop | No | No |
| Wake on request | No | No |
| HTTPS preview URLs | Yes | Yes |
| Raw TCP inbound | Yes | No |
| Public IPv4 | No | No |
| Egress allowlist | No | Yes |
| Secret proxy | Yes | No |
| Secret proxy for any API | Yes | No |
| Preinstalled agents | Yes | No |
| Agent harness API | Yes | No |
| MCP server | No | Yes |
| GPU | No | Yes |
| Windows | No | No |
| Arm64 | No | No |
| Self-hosting | No | Yes |
| BYOC | No | Yes |
| Open source | No | Yes |
| Scoped API keys | Yes | Not published |
| Spend limits | Yes | Not published |
| Usage per sandbox (API) | Yes | No |
| Audit logs | No | Not published |
| SSO | No | No |
| SOC 2 | No | Yes |
| HIPAA | No | Yes |
| EU data residency | Yes | Not published |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement: Beam has no result on the StarSling hpc-sandbox-benchmarks CPU test, so we cannot say which is faster at CPU work. bochka did 26.69 runs per second on that test at 4 vCPU / 8 GB. Beam's own guide says its sandboxes cold-boot in 1 to 3 seconds.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Beam 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 | bochka, a month | Beam, 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 | $20 · $20/mo | $5 · Developer |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $22 · Developer |
| 50 agents in parallel 50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside | $317 · $20/mo × 3 seats | $410 · Team |
| Sandboxes for your users 2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once | $200 · $100/mo × 2 seats | $191 · Team |
| 1,000 short jobs at once 2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month | $2,000 · $2000/mo · with limits | $259 · Team |
bochka: Plans start at $20 a month, and the whole fee is usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.
Beam: Beam sandboxes bill per second for each CPU core (one core is two vCPU) and each GiB of RAM you request, until you terminate them or their time to live ends, so an idle tail is billed too. Beam VMs bill per second for each vCPU and GiB while running, with a 50 GiB root disk included and no compute charge while stopped. Developer has no fee; Team costs $89 a month plus usage, with no usage credit, and there are no egress fees.
Limits in those scenarios
Beam's Developer plan allows 30 CPU containers at once, so 50 parallel agents need the Team plan. Beam does not publish a price for disk beyond what a VM includes, so the scenarios count no disk cost for it. bochka's start limits are lower: at 1,000 short jobs at once, its $2,000 plan queues starts, while Beam's Team plan fits the burst.
| Scenario | bochka | Beam |
|---|---|---|
| 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 Beam when
your agents need GPUs, when you want serverless GPU endpoints and sandboxes in one platform, when you want low-cost CPU VMs in the US, or when you must self-host.
- GPUs in the same platform. For workloads that need a GPU, Beam offers GPU sandboxes and serverless GPUs from RTX 4090 to H100, H200 and B200.
- Outbound rules and US hosting. Teams that need a sandbox locked to a few networks, or hosted in the US, get both.
- Open source and your own cloud. Its Beta9 runtime is AGPL-3.0 and free to self-host, and it can also run in your own cloud for a management fee.
Use bochka when
your agents do real work over hours or days: installs, builds, Docker, emulators and a browser on a full VM whose disk is still there the next time it starts.
- A full VM, not a container. Agents install whatever a task needs. In a gVisor sandbox, tools that expect a real kernel or systemd can fail, and on either Beam product an Android emulator or a nested VM has no /dev/kvm to start on.
- Hosting with access control. An agent that serves a database or a game server over plain TCP cannot be reached on Beam, and a preview in a Beam sandbox is open to anyone with the URL unless the app adds its own auth.
- Agents, desktop and keys built in. On Beam you build the agent harness and any desktop yourself, and secrets sit as environment variables inside a container the agent controls, where one prompt injection can leak them.
Questions people ask
Is bochka cheaper than Beam?
Mostly not on this page. Beam costs less in four of the five scenarios, such as $22 against $26 a month for one agent that never stops, and bochka costs less only for 50 agents in parallel, $317 against $410. For 1,000 short jobs at once, Beam's Team plan also fits the burst while bochka's plans queue the starts.
Is a Beam sandbox a VM?
Not by default. Beam's guide says its sandboxes are containers using runc and gVisor, and its SDK has an opt-in microVM mode for CPU sandboxes. Beam also sells separate CPU VMs with their own kernel and systemd. Every bochka sandbox is a full VM with its own kernel and /dev/kvm.
What happens to files when a Beam sandbox stops?
A Beam sandbox ends when you terminate it or its time to live runs out, which is 10 minutes by default. To keep files you save a filesystem image or memory snapshot, or attach a volume or durable disk; a Beam VM instead keeps its root disk while stopped. bochka saves the disk every minute and keeps it while the sandbox is stopped.
Can bochka run GPUs like Beam?
No. bochka is CPU only. Beam offers GPU sandboxes and serverless GPUs, so pick Beam for work that needs a GPU.
Can I run Docker in each?
Yes. Beam supports Docker inside a sandbox with docker_enabled, and bochka runs Docker in its full VM. bochka also has systemd and /dev/kvm for emulators and VMs.
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.
Start a sandbox
Install the CLI, then run bochka new.
Product preview
More comparisons
- bochka vs E2B
- bochka vs Daytona
- bochka vs Modal
- bochka vs Vercel Sandbox
- bochka vs Blaxel
- bochka vs Runloop
- bochka vs Tensorlake
- bochka vs Cloudflare Sandbox
- bochka vs exe.dev
- bochka vs Agent 37
- bochka vs Oracle Cloud
- bochka vs IONOS Cloud
- E2B vs Beam
- Daytona vs Beam
- Modal vs Beam
- Vercel Sandbox vs Beam
- Cloudflare Sandbox vs Beam
- Blaxel vs Beam
- Runloop vs Beam
- Tensorlake vs Beam