Blaxel vs Beam
Blaxel gives every sandbox its own kernel in a Firecracker microVM that sleeps when idle and wakes in under 25 ms with its memory. Beam is a serverless GPU platform whose sandboxes are fast gVisor containers, with a separate line of CPU VMs.
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
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. “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 | Beam: 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 Beam is a compromise, since a Beam sandbox has no systemd and ends with its time to live; boat adds /dev/kvm and a real disk. | 10th cheapest of 367 $2,373 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 | 12th cheapest of 366 $2,832 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 Both fit short code runs well: Blaxel sleeps right away and wakes in milliseconds, and Beam sandboxes start in a second or two and go away when the timer ends. | 14th cheapest of 345 $144 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 Beam's Team plan fits 300 users at once, while Blaxel's public tiers stop at 200 at once; boat fits it on a self-serve plan too. | 101st of 361, with limits $926 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 | 77th of 360, with limits $4,378 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 | 136th of 364, with limits $704 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 Both fit CI jobs, but builds that need /dev/kvm, like Android emulators, have no documented path on either; a boat sandbox exposes /dev/kvm. | 57th cheapest of 377 $431 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 Blaxel bills RAM whenever a connection is open and has no native SSH; boat is a plain machine you SSH into. | 265th of 368, with limits $114 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 Blaxel runs a desktop and a browser for computer use, and Beam has no desktop or browser product; boat streams a 60fps desktop with Chromium. | 14th cheapest of 369 $634 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 | 16th cheapest of 367 $317 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 | 16th cheapest of 346 $215 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 | 147th of 338, with limits $4,292 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 Blaxel fits with domain-level egress rules and a microVM per sandbox, while Beam's gVisor containers are a compromise; boat gives root with raw TCP. | 3rd cheapest of 360 $217 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 to H100 and B200; Blaxel and boat 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 | Blaxel | Beam | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | gVisor container by default for sandboxes; 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 | No: Firecracker guests do not get /dev/kvm | Not documented | Yes: /dev/kvm, so Android emulators and VMs run inside |
| SSH and systemd | Root and a terminal through bl connect; no native SSH | Root in sandboxes; systemd only in Beam VMs, not in sandboxes | Real SSH, root and systemd, like a normal Ubuntu server |
| Docker inside | Yes, with a Docker-in-sandbox image | Yes, with docker_enabled | Yes |
| Idle and wake | Standby a few seconds after the last connection; wakes in under 25 ms with memory and processes | A sandbox runs until you terminate it or its time to live ends (10 minutes by default), and the idle tail is billed | Stop keeps the disk and costs nothing; resume boots the VM again |
| Disk between runs | Files live in memory (about half the RAM); one block volume can be attached at creation | 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 | A real disk, saved every minute and on stop, kept for free while stopped |
| GPUs | No, CPU only | GPU sandboxes and serverless GPUs up to H100, H200 and B200 | No, CPU only |
| Desktop and computer use | Desktop and browser for computer use | No desktop or browser product | Linux desktop streamed at 60fps with Chromium and computer use |
| Inbound access | Preview URL per port, public or token-protected; no raw TCP or 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; own IPv4 or IPv6 |
| Outbound rules | Domain allow and deny lists, method and path rules, static egress IPs | Block all outbound traffic, or allow up to 10 CIDR ranges, changeable while running | Open internet; filter inside the VM with nftables |
| Keeping API keys out | Proxy fills secrets into outbound HTTPS requests (public preview) | 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 |
| Coding agents | Claude Code image you drive from its terminal or your own harness | None preinstalled; you install and run them through process exec | Seven agents preinstalled, driven from outside with a prompt, steer and events API |
| Regions | Oregon, North Virginia, London, Frankfurt | US only; no other region is listed | EU only: Germany, Finland, France |
| Self-hosting | No | Beta9 runtime is AGPL-3.0 and free to self-host; bring your own cloud for a fee | No |
Every feature Battleships tracks (43)
| Feature | Blaxel | Beam | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | No | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | No | No | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | Yes | No | Yes |
| Computer-use API | Yes | No | Yes |
| SSH | No | 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 | Yes | 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 | No | No | Yes |
| MCP server | Yes | Yes | No |
| GPU | No | Yes | No |
| Windows | No | No | No |
| Arm64 | No | 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 | No | Not published | Yes |
| Usage per sandbox (API) | Yes | No | Yes |
| Audit logs | Not published | Not published | No |
| SSO | Yes | No | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Yes | Yes | No |
| EU data residency | Yes | Not published | Yes |
| Zero data retention | Yes | Not published | Yes |
Performance
On the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU and 8 GB, run on September 29, 2026, boat did 26.69 runs per second and Blaxel 19.48, so boat does about 1.4 times the work in the same time. Beam has no result on this test, so we cannot say how fast it is at CPU work. 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. Blaxel measured on: Sandbox (active time, RAM-only pricing, CPU bundled). 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 | Blaxel, a month | Beam, 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 | $5 · Developer | $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 | $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 | $1,489 · Pay-as-you-go Tier 1 | $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 | $396 · Pay-as-you-go Tier 2 · with limits | $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 | $876 · Pay-as-you-go Tier 2 · with limits | $259 · Team | $2,000 · $2000/mo · with limits |
Blaxel: Blaxel charges for allocated RAM per second while a sandbox is active, meaning a connection is open, with CPU included (8 GB comes with 4 cores). In standby you pay only snapshot storage, and volumes are billed on their full size.
Beam: Beam sandboxes bill per second for each CPU core (two vCPU) and each GiB of RAM you request until you terminate them or their time to live ends, and Beam VMs bill only while running. Developer has no fee; Team costs $89 a month plus usage, with no usage credit.
Beam: 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.
Limits in those scenarios
Blaxel's self-serve tiers allow 10, 50 or 200 sandboxes at once, and standby sandboxes count, so 300 users or 1,000 jobs at once need a sales tier; its lower tiers also delete sandboxes after 7 or 30 days. Beam's Developer plan allows 30 CPU containers at once, so 50 agents need Team, which fits every scenario. Beam publishes no price for disk beyond what a VM includes, so its prices count no disk. boat queues starts at 1,000 short jobs at once.
| Scenario | Blaxel | Beam | 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, when you want a microVM per sandbox, or when you need fine outbound rules in the US or Europe.
- Sleeps in seconds, wakes in milliseconds. For sandboxes that sit idle most of the time: Blaxel sleeps after the last connection and wakes in under 25 ms with its memory.
- A real kernel per sandbox. Every Blaxel sandbox is a Firecracker microVM with its own kernel, while a Beam sandbox is a gVisor container unless you use Beam VMs.
- Fine outbound rules, US and Europe. Teams that lock agents to chosen domains, methods and paths get that, with regions in the US, London and Frankfurt.
Use Beam when
your agents need GPUs, when you start large bursts of short sandboxes on a self-serve plan, when you want low-cost CPU VMs in the US, or when you must self-host.
- GPUs in the same platform. For work that needs a GPU, Beam offers GPU sandboxes and serverless GPUs from RTX 4090 to H100, H200 and B200.
- Big bursts on a self-serve plan. Beam's Team plan allows 1,000 CPU containers at once, so 300 users or 1,000 short jobs fit without a sales call.
- Open source and your own cloud. Teams that must self-host can run the AGPL-3.0 Beta9 runtime for free, or run Beam in their own cloud for a fee.
Where boat fits
Blaxel and Beam are both good at short, quick sandboxes. If your agents instead work for hours on builds, tests, Docker and emulators, boat gives each one a whole Linux machine with a disk that stays and agents built in. It also has the fastest CPU of the three where measured.
A whole Linux machine
Neither Blaxel's Firecracker guests nor Beam document /dev/kvm, so an Android emulator or a nested VM will not start. Beam sandboxes also have no systemd; getting it means moving to Beam VMs, a separate product.
A disk that stays
Blaxel keeps files in memory, about half the RAM, so a big repo fills it unless you attach a volume at creation. A Beam sandbox ends with its time to live unless you save an image or use a volume.
Agents and hosting built in
On Blaxel and Beam you build the agent harness yourself, and neither offers raw TCP. boat drives seven preinstalled agents from outside and serves HTTPS on 50 token-protected ports.
Use boat when your agents do real work for hours: builds, tests, Docker and emulators on a whole Linux machine with a disk that stays, a faster CPU and agents built in. Compare it one to one: boat vs Blaxel and boat vs Beam.
Questions people ask
Is Blaxel cheaper than Beam?
No, Beam costs less in all five scenarios we priced: $22 against $120 for one agent that never stops, and $410 against $1,489 for 50 agents in parallel. Beam publishes no disk price, so its numbers count no disk, and Blaxel bills only while a connection is open, so a workload that disconnects often pays less.
Which is faster, Blaxel or Beam?
We cannot say for CPU work: Blaxel did 19.48 runs per second on the hpc-sandbox-benchmarks test, and Beam has no result there. boat did 26.69 on the same test. For waking up, Blaxel resumes from standby in under 25 ms, and Beam says its sandboxes cold-boot in 1 to 3 seconds.
Is a Beam sandbox a VM like Blaxel?
Not by default. A Beam sandbox is a container isolated with gVisor, while every Blaxel sandbox is a Firecracker microVM with its own kernel. Beam also sells separate CPU VMs with their own kernel and systemd.
Can Blaxel and Beam run Docker?
Yes. Blaxel runs Docker with its Docker-in-sandbox image, and Beam with docker_enabled. Neither documents /dev/kvm for Android emulators or nested VMs, which boat exposes in every sandbox.
Does Blaxel have GPUs?
No, Blaxel is CPU only, and so is boat. Beam offers GPU sandboxes and serverless GPUs from RTX 4090 up to H100, H200 and B200, so pick Beam for work that needs a GPU.
Where do Blaxel and Beam run?
Blaxel runs in Oregon, North Virginia, London and Frankfurt. Beam runs in the United States on AWS and Google Cloud, with no other region listed. boat runs only in the EU, in Germany, Finland and France.
Try boat
Install the CLI, then run boat new.
7-day free trial