Runloop vs Beam
Runloop is built for coding agents: each devbox is a micro-VM with blueprints, agent gateways and a desktop. Beam is a serverless GPU cloud whose sandboxes are quick gVisor containers, with GPUs, self-hosting and a separate line of CPU VMs.
The companies and products
Runloop
Runloop is a US platform of sandboxes, called devboxes, for building, running and testing AI coding agents.
You get Linux devboxes built from Dockerfile-style blueprints, disk snapshots, HTTPS tunnels, agent gateways that hide API keys, and Axons, event streams that drive agents such as Claude Code. Each devbox runs in a micro-VM on Runloop's own bare-metal hypervisor, with a container layer inside. It is built for teams shipping coding agents, plus evaluation and RL fine-tuning work on the Enterprise plan.
- Compliance
- SOC 2 Type 2
- Architectures
- x86_64 and arm64 base blueprints
- Own-cloud deploy
- Deploy to VPC on AWS, GCP and Azure (Enterprise)
- Regions
- Not documented or selectable
- Company
- Runloop AI, Inc.
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. “20th cheapest of 367” means 19 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 | Runloop: price rank | Beam: price rank | bochka: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Runloop fits a software factory fully with micro-VMs and Docker-in-Docker, while a Beam sandbox ends with its time to live and has no systemd; bochka adds /dev/kvm and keeps the disk on every plan. | 20th cheapest of 367 $8,152 a month | 69th of 367, with limits $551 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB | 32nd cheapest of 366 $10,194 a month | 115th of 366, with limits $651 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 Beam suits many short code runs: sandboxes start in a second or two, bill per second and go away when the timer ends. | 44th cheapest of 345 $525 a month | 8th cheapest of 345 $117 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 | 26th cheapest of 361 $3,301 a month | 3rd cheapest of 361 $290 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 Runloop is built for RL rollouts, with large waves of devboxes and RL fine-tuning on Enterprise; Beam is only a compromise here. | 4th cheapest of 360 $15,922 a month | 341st of 360, with limits $939 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 | 81st cheapest of 364 $2,562 a month | 13th cheapest of 364 $251 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 Docker works inside all three; bochka's CPUs ran about three times faster than Runloop's on the same build-and-test benchmark, and Beam has no comparable result. | 121st cheapest of 377 $1,554 a month | 12th cheapest of 377 $171 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Beam VMs keep a 50 GiB root disk while stopped, while a Runloop devbox running all month needs an idle policy in place of its 48-hour lifetime setting. | 113th cheapest of 368 $410 a month | 13th cheapest of 368 $21 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 Runloop ships a desktop and a browser your agent can control, Beam has none, and bochka streams its desktop at 60fps. | 39th cheapest of 369 $2,306 a month | 111th of 369, with limits $237 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 | 40th cheapest of 367 $1,153 a month | 195th of 367, with limits $176 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 | 68th cheapest of 346 $781 a month | 200th of 346, with limits $131 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 | 266th of 338, with limits $15,611 a month | 42nd of 338, with limits $923 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 Runloop can lock each devbox to a hostname allowlist and Beam to up to 10 CIDR ranges; bochka gives each one a full kernel with nested virtualization. | 10th cheapest of 360 $770 a month | 175th of 360, with limits $155 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 Only Beam has GPUs, from RTX 4090 up to H100 and B200; Runloop and bochka are CPU only. | Can't run it | Cheapest of 98 $458 a month | 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 | Runloop | Beam | bochka |
|---|---|---|---|
| Isolation | Micro-VM on a custom bare-metal hypervisor, plus a container layer | gVisor container by default; separate Beam VMs are CPU microVMs with their own kernel | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Nested virtualization | Not documented; Docker-in-Docker blueprints only | Not documented | Yes: /dev/kvm for Android emulators and VMs inside |
| Docker and systemd | Docker on the dnd blueprints, as root | Docker with docker_enabled; systemd only in Beam VMs, not in sandboxes | Docker, systemd and root, like a normal Ubuntu server |
| Images | Blueprints built from Dockerfiles, x86_64 and arm64 | Custom images, saved filesystem images and memory snapshots | Templates from named snapshots, x86_64 only, no Dockerfile builds |
| Lifetime | 1 hour by default, 48 hours max, or no cap with an idle policy | 10 minutes by default; set -1 to run until you terminate it | No session cap on paid plans; you set the time to live |
| Keeping files | Disk kept through suspend (Pro plan) or manual disk snapshots; shutdown ends the devbox | 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 | Disk saved every minute and on stop, on every plan; a stopped sandbox keeps it for free |
| Snapshots and fork | Disk snapshots, and suspend with wake on an HTTP request (Pro) | Memory snapshot of a running sandbox with its processes, restored into new sandboxes | Fork a running sandbox with its disk |
| GPUs | No | GPU sandboxes and serverless GPUs up to H100, H200 and B200 | No, CPU only |
| Desktop and browser | Desktop and browser your agent can control | No desktop or browser product | Linux desktop streamed at 60fps with Chromium and computer use |
| Inbound access | One HTTPS tunnel per devbox, open or bearer token; SSH through a TLS proxy; no public IP | Public HTTPS URL per exposed port with no built-in auth; no raw TCP or dedicated IP | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6 |
| Outbound rules | Hostname allowlist with wildcards, or block all | Block all, or allow up to 10 CIDR ranges, changeable while running | Open internet, no provider-side allowlist |
| Coding agents | Claude Code, Codex, OpenCode, Gemini CLI, DeepAgents, driven through Axons | None preinstalled; you install and run them through process exec | Seven agents preinstalled, with a prompt, steer and events API |
| Keeping API keys out | Agent gateways for any API endpoint with bearer, header or basic auth | Secrets are environment variables inside the sandbox | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Where it runs | Regions not documented; Deploy to VPC on AWS, GCP or Azure (Enterprise) | US only; Beta9 runtime is AGPL-3.0 and free to self-host | EU only (Germany, Finland, France), EU data residency |
Every feature Battleships tracks (43)
| Feature | Runloop | Beam | bochka |
|---|---|---|---|
| Full VM (own kernel) | Yes | No | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | No | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | Yes | No | Yes |
| Computer-use API | Yes | No | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | No | Yes |
| Automatic snapshots | Yes | No | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | Yes | Yes |
| Memory fork | No | Yes | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | No | No |
| Wake on request | Yes | No | 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 | No | Yes |
| Secret proxy for any API | Yes | No | Yes |
| Preinstalled agents | Yes | No | Yes |
| Agent harness API | Yes | No | Yes |
| MCP server | Yes | Yes | No |
| GPU | No | Yes | No |
| Windows | No | No | No |
| Arm64 | Yes | No | No |
| Self-hosting | No | Yes | No |
| BYOC | Yes | Yes | No |
| Open source | No | Yes | No |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | No | No | Yes |
| Audit logs | Not published | Not published | No |
| SSO | Yes | No | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Not published | Yes | No |
| EU data residency | No | Not published | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
On the StarSling hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB (run 36498291449, 2026-09-29), bochka scored 26.69 runs a second and Runloop 8.29, about 3.2 times apart. Beam has no result on that test, so we cannot say how its CPUs compare. 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 | Runloop, a month | Beam, 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 | $113 · Basic | $5 · Developer | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $429 · Basic | $22 · Developer | $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 | $5,268 · Basic | $410 · 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 | $1,441 · Basic | $191 · Team | $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 | $3,184 · Basic | $259 · Team | $2,000 · $2000/mo · with limits |
Runloop: Runloop bills per second for the CPU and memory you allocate, while a devbox starts, runs, suspends or resumes, and bills its disk for the devbox's whole life. Basic has no plan fee; Pro adds $250 a month that is not usage credit and unlocks suspend and resume.
Beam: Beam sandboxes bill per second for each CPU core (two vCPU) and GiB of RAM you request, until you terminate them or their time to live ends, so an idle tail is billed too. Developer has no fee; Team is $89 a month plus usage with no credit, and there are no egress fees.
Beam: Plans start at $20 a month and the whole fee is usage credit, billed per second while a sandbox runs. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
Runloop's lifetime setting defaults to 1 hour and tops out at 48 hours unless an idle policy replaces it, and it publishes no egress price. Beam's Developer plan allows 30 CPU containers at once, so 50 parallel agents need Team, and Beam publishes no disk price, so the scenarios count no disk cost for it. Both fit 1,000 short jobs at once, while bochka's start limits queue that burst even on its $2,000 plan.
| Scenario | Runloop | Beam | bochka |
|---|---|---|---|
| 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 Runloop when
you build coding agents and want micro-VM devboxes with a desktop, hostname allowlists, Dockerfile blueprints, arm64 or devboxes inside your own cloud.
- Made for coding agents. Teams shipping coding agents get micro-VM devboxes, a desktop, agent gateways and agents such as Claude Code driven through Axons.
- Hostname allowlists. If a devbox must reach only named hosts, Runloop allows listed hostnames with wildcards, which is finer than Beam's CIDR ranges.
- Dockerfiles, arm64 and your own cloud. Runloop builds blueprints from Dockerfiles, offers arm64, and on Enterprise runs devboxes inside your own AWS, GCP or Azure account.
Use Beam when
you need GPUs, many short throwaway sandboxes, low-cost CPU VMs in the US, or a runtime you can self-host.
- GPUs in the same platform. For work that needs a GPU, Beam offers GPU sandboxes and serverless GPUs from RTX 4090 up to H100, H200 and B200.
- Quick, throwaway sandboxes. Sandboxes cold-boot in 1 to 3 seconds, bill per second and end on their own timer, which suits short code runs.
- Open source and self-hosting. Beam's Beta9 runtime is AGPL-3.0 and free to self-host, and Beam can also run in your own cloud for a fee.
Where bochka fits
If your agents do real work for hours, like installs, builds, Docker, emulators and a browser, look at bochka. Each sandbox is a full VM with /dev/kvm and systemd, its disk is saved every minute on every plan, and it ran about three times faster than Runloop on the same CPU test. Pick Runloop or Beam instead for arm64, GPUs, egress allowlists or your own cloud.
A full machine with /dev/kvm
Neither Runloop nor Beam documents /dev/kvm, so an Android emulator or a VM inside will not start. Beam sandboxes also lack systemd, so tools that expect a real Linux server need a Beam VM instead.
Files that stay on every plan
A Runloop devbox is gone after shutdown unless you pay for Pro suspend or write snapshot code. A Beam sandbox ends with its time to live, 10 minutes by default, unless you save an image or attach a volume.
Faster CPUs and open hosting
On the same build-and-test test bochka ran 26.69 runs a second and Runloop 8.29, so agent waits take longer there. Runloop and Beam reach machines over HTTPS only, so a raw TCP server has no way in.
Use bochka when your agents do real work for hours on a full VM with /dev/kvm, systemd and a 60fps desktop, on fast CPUs, with files kept on every plan. Compare it one to one: bochka vs Runloop and bochka vs Beam.
Questions people ask
Is Runloop cheaper than Beam?
No, in every scenario here Beam costs less. One agent that never stops costs $429 a month on Runloop and $22 on Beam, and 50 agents in parallel cost $5,268 against $410. bochka costs $26 and $317 for those two.
Which is faster, Runloop or Beam?
We cannot say: Runloop scored 8.29 runs a second on the hpc-sandbox-benchmarks CPU test and Beam has no result there. bochka scored 26.69 on the same test.
Is a Beam sandbox a VM like a Runloop devbox?
Not by default. Beam sandboxes are gVisor containers, with separate Beam VMs as CPU microVMs. Each Runloop devbox runs in a micro-VM, and each bochka sandbox is a full VM with its own kernel.
Can Runloop and Beam run Docker?
Yes. Runloop runs Docker on its Docker-in-Docker blueprints, and Beam supports Docker in a sandbox with docker_enabled. bochka runs Docker in a full VM with systemd and /dev/kvm.
Does Runloop or Beam have GPUs?
Only Beam. It offers GPU sandboxes and serverless GPUs from RTX 4090 up to H100, H200 and B200. Runloop and bochka are CPU only.
What happens to files when a sandbox stops?
A Runloop devbox keeps its disk only while suspended on Pro or in a snapshot. A Beam sandbox ends with its time to live unless you save an image or use a volume, while a Beam VM keeps its root disk. bochka saves the disk every minute and keeps it while stopped.
Try bochka
Install the CLI, then run bochka new.
Product preview