Blaxel vs Azure Container Apps Sandboxes
Both give each sandbox its own kernel and can save memory while it sleeps. Blaxel is a standalone agent platform that drops to standby seconds after the last connection, while Azure Container Apps Sandboxes lives inside your Azure account with Azure networking, identity and 40 regions.
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
Azure Container Apps Sandboxes
Azure Container Apps Sandboxes is a service inside Microsoft Azure that gives each agent or user an isolated microVM you create, suspend and resume through an SDK.
It is part of Azure Container Apps, the hyperscaler's serverless container platform, and lives in your Azure subscription as a sandbox group resource. Each sandbox boots from an OCI image or a snapshot, has its own kernel, and can be suspended with its memory and resumed in under a second. It is built for teams already on Azure that want stateful code execution with Azure networking, identity and billing.
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 | Azure Container Apps Sandboxes: 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 Azure is a compromise there; boat adds SSH, /dev/kvm for emulators and a real disk that stays. | 10th cheapest of 367 $2,373 a month | 288th of 367, with limits $5,276 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 | 302nd of 366, with limits $6,544 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 are built for this: short runs that sleep with their memory and come back fast, Blaxel in under 25 ms and Azure in under a second. | 14th cheapest of 345 $144 a month | 34th cheapest of 345 $354 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 Azure fits 300 users at once on pay-as-you-go, while Blaxel's public tiers stop at 200 at once; boat fits them on a self-serve plan. | 101st of 361, with limits $926 a month | 22nd cheapest of 361 $2,260 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 | 153rd of 360, with limits $10,740 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 Azure fits evals without a sales call, while Blaxel's public tiers cap how many run at once at 200. | 136th of 364, with limits $704 a month | 75th cheapest of 364 $1,728 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 | 103rd cheapest of 377 $1,046 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Neither has native SSH, so a dev box on either goes through its own CLI; boat is a plain machine you SSH into and leave on. | 265th of 368, with limits $114 a month | 322nd of 368, with limits $262 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 ships a desktop and browser for computer-use agents, Azure's sandboxes are headless, and boat streams a 60fps desktop. | 14th cheapest of 369 $634 a month | 279th of 369, with limits $1,573 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 Blaxel has browser control built in, while on Azure you install and run a headless browser yourself. | 16th cheapest of 367 $317 a month | 288th of 367, with limits $795 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 | 284th of 346, with limits $561 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 | 239th of 338, with limits $10,956 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 parallel red teaming well, with domain-level egress rules; boat adds root with raw TCP inbound. | 3rd cheapest of 360 $217 a month | 278th of 360, with limits $517 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 | Azure Container Apps Sandboxes | boat |
|---|---|---|---|
| Isolation | Firecracker microVM per sandbox, own kernel | MicroVM per sandbox with its 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 for Android emulators and VMs |
| Getting a shell | Root, terminal through the bl connect command, no native SSH | Interactive shell through the aca CLI, SDK or portal; no SSH | Real SSH, plus CLI and API exec |
| Docker inside | Yes, with a Docker-in-sandbox image | Depends on the image: azure-dev ships Docker; the default ubuntu image has only Buildah | Docker, systemd and root on every sandbox |
| Disk | Files live in memory (about half the RAM); one block volume can be attached at creation | Disk is kept with the sandbox when it stops or suspends | A real disk that stays, snapshotted every minute and on stop |
| Sleep and wake | Standby a few seconds after the last connection, wakes in under 25 ms with memory and processes | Auto-suspend after an idle timeout (5 minutes by default), resumes in under a second with memory; traffic wakes it | Stop keeps the disk and costs nothing; resume boots the VM again |
| Fork | Fork with memory and running processes (private preview) | Snapshot a running sandbox with its memory and create new sandboxes from it | Fork a running sandbox with its disk |
| Desktop and browser | Desktop, browser and computer-use control available | Headless; no desktop or managed browser | Linux desktop streamed at 60fps, Chromium and computer-use tools preinstalled |
| Inbound traffic | Preview URL per port, public or token-protected; no raw TCP or public IP | Public HTTPS routes per published port; private endpoint from your VNet at extra cost; no public 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 | Egress policy with allow, deny, rewrite and header rules by host, path and method; VNet integration | Open internet; filter inside the VM with nftables |
| Keeping keys out of the sandbox | Proxy fills secrets into outbound HTTPS requests; the sandbox never sees them (public preview) | Group secrets usable in egress header rules; Copilot and Anthropic tokens are injected into the sandbox at startup | Credentials proxy for model providers and any HTTPS API you register; a credential can switch accounts when credits run out |
| Coding agents | Claude Code image you drive from its terminal or your own harness | Copilot CLI and Claude Code images, run through the exec API | Seven agents preinstalled, with a prompt, steer and events API |
| Scaling up a fleet | 10, 50 or 200 at once on self-serve tiers, standby included; more through sales | 500 concurrent active cores by default; more by Azure support request | Concurrency set by plan, up to 2,000 sandboxes, self-serve |
| Regions | Oregon, North Virginia, London, Frankfurt | 40 Azure regions, 9 of them in the EU | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | Blaxel | Azure Container Apps Sandboxes | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | No | Yes | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | Yes | No | Yes |
| Computer-use API | Yes | No | Yes |
| SSH | No | No | 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 | Yes | 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 | No | 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 | No | No |
| Open source | No | No | No |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | No | Yes | Yes |
| Usage per sandbox (API) | Yes | Yes | Yes |
| Audit logs | Not published | Yes | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Yes | Yes | No |
| EU data residency | Yes | Yes | Yes |
| Zero data retention | Yes | Not published | Yes |
Performance
On the StarSling hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU and 8 GB, in the same run on September 29, 2026, boat did 26.69 runs per second and Blaxel 19.48. That is about 1.4 times the work in the same time for boat. Azure Container Apps Sandboxes has no comparable measurement yet, so this page makes no speed claim for it.
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). Azure Container Apps Sandboxes 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 | Azure Container Apps Sandboxes, 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 | $68 · Pay-as-you-go | $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 | $262 · Pay-as-you-go · with limits | $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 | $3,421 · Pay-as-you-go | $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 | $989 · Pay-as-you-go | $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 | $2,148 · Pay-as-you-go | $2,000 · $2000/mo · with limits |
Blaxel: Blaxel charges for allocated RAM per second while a sandbox is active, meaning it has an open connection, with CPU included. In standby you pay only snapshot storage, and self-serve tiers are unlocked by topping up your wallet with usage credit.
Azure Container Apps Sandboxes: Azure bills per second on the Container Apps Consumption meters for the vCPU and memory of the sandbox's tier while it runs, including idle time before auto-suspend (5 minutes by default). There is no plan fee, and some regions such as West Europe and UK South charge more.
Azure Container Apps Sandboxes: 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
Blaxel's self-serve tiers allow 10, 50 or 200 sandboxes at once, standby included, so the 300-user and 1,000-job scenarios need a sales tier, and Tiers 0 and 1 delete sandboxes after 7 or 30 days. Azure fits both of those, but it bills every running second until a sandbox suspends, so the always-on scenario only gets close with a 3-year commitment, and its 500-core default quota caps a fleet until support raises it. boat fits every scenario but the 1,000-job burst, where its $2,000 plan queues starts.
| Scenario | Blaxel | Azure Container Apps Sandboxes | boat |
|---|---|---|---|
| One coding agent, workdays | None that bite | 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 | None that bite |
| Sandboxes for your users |
| None that bite | None that bite |
| 1,000 short jobs at once |
| None that bite |
|
Which one should you use?
Use Blaxel when
your sandboxes sit idle most of the time and must wake in milliseconds with their memory, outside any cloud account, or when your agents need a desktop and browser.
- Sleeps in seconds, wakes in milliseconds. For sandboxes that sit idle most of the time: standby seconds after the last connection, back in under 25 ms.
- A standalone agent platform. No cloud account to set up: sandboxes, batch jobs, MCP server hosting and a model gateway come from one provider.
- Desktop and browser included. Computer-use and browser agents get a desktop and browser control, where Azure's sandboxes are headless.
Use Azure Container Apps Sandboxes when
your team already runs on Azure, wants Entra ID, VNets and strict egress rules, needs regions outside the US and Europe, or must start hundreds of sandboxes at once.
- Inside your Azure account. Teams already on Azure get Entra ID, Azure billing and VNets to reach their private resources.
- 40 regions. Azure runs sandboxes in 40 regions on six continents, where Blaxel runs in four.
- No public cap on sandboxes at once. The default quota is 500 active cores, raised by support request, so 300 or 1,000 at once fits without a sales tier.
Where boat fits
Blaxel and Azure are both built for sandboxes that sleep with their memory between short bursts of work. If your agents work for hours on builds, tests, Docker and emulators, or need a screen and SSH, boat gives each one a whole Linux machine with a real disk and agents built in.
A whole machine with /dev/kvm and SSH
Neither Blaxel nor Azure gives you /dev/kvm, so an Android emulator or nested VM will not start, and neither has native SSH, so remote editors and scp go through bl connect or the aca CLI.
A disk that stays, and a measured faster CPU
Blaxel keeps files in memory, about half the RAM, unless you attach a volume at creation. boat saves a real disk every minute and ran 26.69 runs per second against Blaxel's 19.48; Azure has no comparable measurement.
Agents and keys handled from outside
On both, you build your own harness around a Claude Code image. Azure injects agent tokens into the sandbox at start, where a prompt-injected agent can read them; boat keeps keys in a proxy outside and drives agents through one API.
Use boat when your agents do real work for hours: builds, tests, Docker and emulators on a whole Linux machine with SSH, a real disk, a 60fps desktop and coding agents built in. Compare it one to one: boat vs Blaxel and boat vs Azure Container Apps Sandboxes.
Questions people ask
Is Blaxel cheaper than Azure Container Apps Sandboxes?
In every scenario we priced, Blaxel costs less: one coding agent on workdays is $33 against $68 a month, and 50 agents in parallel $1,489 against $3,421. But Blaxel's self-serve tiers do not fit 300 users or 1,000 jobs at once, which Azure does. boat is $20 and $317 for those first two.
Which is faster, Blaxel or Azure Container Apps Sandboxes?
Only Blaxel has a comparable CPU measurement: 19.48 runs per second on a Node.js build-and-test loop at 4 vCPU and 8 GB. Azure has not been measured on the same test. boat did 26.69 on it.
Can Blaxel or Azure run Docker?
Both can with the right image: Blaxel has a Docker-in-sandbox image, and Azure's azure-dev image ships Docker while its default ubuntu image has only Buildah. boat runs Docker on every sandbox.
Can I SSH into Blaxel or Azure sandboxes?
Neither has native SSH. Blaxel gives you a terminal through bl connect, and Azure an interactive shell through the aca CLI, SDK or portal. Every boat sandbox has a real SSH server.
Can they run an Android emulator?
An emulator needs /dev/kvm. Blaxel's Firecracker guests do not get it, and Azure does not document nested virtualization. boat exposes /dev/kvm inside every sandbox.
Do I need an Azure account?
For Azure Container Apps Sandboxes, yes: an Azure subscription, a Microsoft Entra ID account and the Container Apps SandboxGroup Data Owner role. Blaxel and boat each have their own sign-up.
Try boat
Install the CLI, then run boat new.
7-day free trial