Azure Container Apps Sandboxes vs Upstash Box

Azure gives each sandbox a microVM with its own kernel that suspends with its memory, inside your Azure account in 40 regions. Upstash Box gives each agent a light Docker container in AWS us-east-1 that pauses when idle, bills only the CPU it uses and comes with coding agents built in.

The companies and products

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.

Upstash Box

Upstash Box is a cloud computer for AI agents from Upstash, the company known for serverless Redis, Vector and QStash.

Each box is a Docker container with its own filesystem, shell, git and an optional coding agent such as Claude Code, Codex or OpenCode, which you drive from TypeScript or Python SDKs. A box pauses when it sits idle, keeps its files, and you pay for the CPU it actually uses. Upstash built it to run its own Context7 service and opened it to everyone in March 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. “34th cheapest of 345” means 33 of the other 344 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 workloadAzure Container Apps Sandboxes: price rankUpstash Box: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
A software factory needs Docker and long builds; Upstash has no Docker inside, Azure needs the azure-dev image for it, and boat has Docker and /dev/kvm on every sandbox.
288th of 367, with limits
$5,276 a month
61st of 367, with limits
$464 a month
3rd cheapest of 367
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
302nd of 366, with limits
$6,544 a month
103rd of 366, with limits
$475 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; Upstash ranks 10th and Azure 34th, and Azure is the one that can suspend a running interpreter with its memory.
34th cheapest of 345
$354 a month
10th cheapest of 345
$119 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
All three fit; boat ranks 1st and Upstash 2nd at close prices, while Azure ranks 22nd at about ten times Upstash's cost.
22nd cheapest of 361
$2,260 a month
2nd cheapest of 361
$222 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
153rd of 360, with limits
$10,740 a month
352nd of 360, with limits
$8,068 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
All three fit agent evals; boat ranks 10th, Upstash 52nd and Azure 75th.
75th cheapest of 364
$1,728 a month
52nd cheapest of 364
$1,011 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
Neither Azure nor Upstash documents nested virtualization for Android or VM builds, and Upstash has no Docker inside; boat ranks 4th here with both.
103rd cheapest of 377
$1,046 a month
120th cheapest of 377
$1,520 a month
4th cheapest of 377
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
A flat-price keep-alive box makes Upstash a cheap light dev box, while Azure bills a running sandbox every second and has no SSH.
322nd of 368, with limits
$262 a month
10th cheapest of 368
$20 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
Both are headless with no desktop; boat streams a Linux desktop at 60fps so a computer-use agent has a screen to look at.
279th of 369, with limits
$1,573 a month
73rd of 369, with limits
$76 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
Upstash ships a managed headless Chromium with AI page actions, Azure ships no browser image, and boat gives the agent a desktop browser it can see.
288th of 367, with limits
$795 a month
49th of 367, with limits
$38 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
284th of 346, with limits
$561 a month
37th cheapest of 346
$400 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
239th of 338, with limits
$10,956 a month
200th of 338, with limits
$8,000 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
278th of 360, with limits
$517 a month
225th of 360, with limits
$259 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 itCan't run itCan't run it
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Can't run itCan't run itCan't run it

Key features

FeatureAzure Container Apps SandboxesUpstash Boxboat
IsolationMicroVM per sandbox with its own kernelDocker container per box on AWSFull VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Docker insideDepends on the image: azure-dev ships Docker on systemd; the default ubuntu image has only BuildahNot documented; the box is itself a Docker container, and custom images are listed as coming soonDocker, systemd and root on every sandbox
Nested virtualizationNot documentedNo; boxes are containers with no VM support documentedYes, /dev/kvm for Android emulators and VMs
Getting a shellInteractive shell through the aca CLI, SDK or portal; no SSHSSH through a gateway, plus SDK execSSH, plus CLI and API exec
Biggest machineTiers up to 4 cores / 8 GB; up to 16 vCPU / 32 GB by APILarge: 8 vCPU / 16 GBUp to 16 vCPU / 32 GB on the $100 plan and above
Suspend and resumeSuspend with memory and disk; resume in under a second with processes runningPauses itself when idle and keeps its files; storage keeps billing while pausedDisk saved every minute and on stop; a stopped sandbox costs nothing
Wake on requestYes; network traffic or a start command brings a suspended sandbox backYes; a request to a public URL resumes a paused box and waits for the appNo; a stopped sandbox is started by API
ForkSnapshot a running sandbox with its memory and create new sandboxes from itSnapshot a running box's files and start many new boxes from itFork a running sandbox with its disk
Desktop and browserHeadless; no desktop or managed browserManaged headless Chromium with AI page actions and CDP; no desktopLinux desktop streamed at 60fps, Chromium and computer-use tools preinstalled
Inbound accessPublic HTTPS routes per published port; private endpoint from your VNet at extra cost; no public IPHTTPS URL per port, public unless you add a token or basic auth; no raw TCPHTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6
Outbound rulesAllow, deny, rewrite and header rules by host, path and method; VNet integrationAllow all, deny all, or allow and deny by domain and CIDR, changeable on a running boxOpen internet, no provider-side allowlist
Coding agentsCopilot CLI and Claude Code images, run through the exec APIClaude Code, Codex and OpenCode built in, with run and stream APIs, webhooks and scheduled promptsSeven agents preinstalled, with a prompt, steer and events API
Keeping API keys out of the sandboxGroup secrets usable in egress header transforms; Copilot and Anthropic tokens are injected into the sandbox at startupHost proxy injects headers into outbound HTTPS on port 443; set when the box is createdCredentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Regions40 Azure regions, 9 of them in the EUUS only (AWS us-east-1)EU only (Germany, Finland, France)
Every feature Battleships tracks (43)
FeatureAzure Container Apps SandboxesUpstash Boxboat
Full VM (own kernel)YesNoYes
Docker insideYesNoYes
Nested virtualizationNoNoYes
RootYesNot publishedYes
SystemdYesNot publishedYes
Desktop GUINoNoYes
BrowserNoYesYes
Computer-use APINoNoYes
SSHNoYesYes
Persistent diskYesYesYes
Pause/resumeYesYesYes
Automatic snapshotsYesNoYes
Fork/cloneYesYesYes
Live fork (no pause)YesYesYes
Memory forkYesNoNo
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesYesYes
Idle auto-stopYesYesNo
Wake on requestYesYesNo
HTTPS preview URLsYesYesYes
Raw TCP inboundNoNoYes
Public IPv4NoNoNo
Egress allowlistYesYesNo
Secret proxyYesYesYes
Secret proxy for any APIYesYesYes
Preinstalled agentsYesYesYes
Agent harness APINoYesYes
MCP serverNoYesNo
GPUNoNoNo
WindowsNoNoNo
Arm64NoYesNo
Self-hostingNoNoNo
BYOCNoNoNo
Open sourceNoNoNo
Scoped API keysNot publishedNot publishedYes
Spend limitsYesNot publishedYes
Usage per sandbox (API)YesYesYes
Audit logsYesNot publishedNo
SSOYesNoNo
SOC 2YesYesNo
HIPAAYesNoNo
EU data residencyYesNoYes
Zero data retentionNot publishedNot publishedYes

Performance

Azure Container Apps SandboxesNot measured
Upstash BoxNot measured
boat26.69 runs/s

Neither Azure Container Apps Sandboxes nor Upstash Box has a result on the hpc-sandbox-benchmarks CPU test, so there is no comparable speed measurement between them. boat did 26.69 runs per second on that Node.js build-and-test loop at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts. This page makes no speed claim about Azure or Upstash.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Azure Container Apps Sandboxes and Upstash Box have 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.

ScenarioAzure Container Apps Sandboxes, a monthUpstash Box, a monthboat, 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
$68 · Pay-as-you-go$21 · Pay as You Go$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$262 · Pay-as-you-go · with limits$21 · Pay as You Go$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
$3,421 · Pay-as-you-go$900 · Pay as You Go · with limits$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
$989 · Pay-as-you-go$306 · 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
$2,148 · Pay-as-you-go$1,822 · Pay as You Go$2,000 · $2000/mo · with limits

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, idle time before auto-suspend included. There is no plan fee, stopped sandboxes pay no CPU or memory, and some regions such as West Europe and UK South charge more.

Upstash Box: A standard box is billed for the CPU it actually uses, at $0.10, $0.20 or $0.40 per active CPU hour for Small, Medium and Large, plus $0.10 per GB-month of storage, and RAM is free. A keep-alive box costs a flat $8, $16 or $32 a month whether it is busy or not.

Limits in those scenarios

Azure bills a running sandbox every second until it suspends, so one agent that never stops costs $262 a month and only gets close with a 3-year commitment. A default quota of 500 active cores also caps an Azure fleet until support raises it. Upstash has no Docker inside a box, so the 50-agent scenario does not fit there, its disks stop at 5, 10 or 20 GB by size, and its egress price is not published.

ScenarioAzure Container Apps SandboxesUpstash Boxboat
One coding agent, workdaysNone that bite
  • flat pool: the tier is billed whether used or not
  • egress price not published
None that bite
One agent that never stops
  • 3-year commitment
  • flat pool: the tier is billed whether used or not
  • egress price not published
None that bite
50 agents in parallelNone that bite
  • missing Docker inside
  • flat pool: the tier is billed whether used or not
  • egress price not published
None that bite
Sandboxes for your usersNone that bite
  • egress price not published
None that bite
1,000 short jobs at onceNone that bite
  • egress price not published
  • max 2,400 starts/day (needs ~6,667)
  • max 600 starts/hour (needs ~1,000)
  • bursts above 90 starts/min are queued (a burst of 333 takes ~4 min to start)

Which one should you use?

Use Azure Container Apps Sandboxes when

your team already runs on Azure and wants sandboxes that suspend with their memory, sit behind strict egress rules and VNets, or run in many regions.

  • Memory suspend in under a second. Good for stateful jobs that sleep between requests: a sandbox suspends with its memory and resumes with its processes running.
  • Fine-grained outbound rules. Its egress policy can allow, deny or rewrite outbound requests by host, path and method, and reach your private Azure networks.
  • Inside Azure, in 40 regions. Teams already on Azure get Entra ID, Azure billing and VNets, with sandboxes in 40 regions including 9 in the EU.

Use Upstash Box when

your agents mostly wait, should wake on an incoming request, need coding agents ready to drive from an SDK, and can run in the US.

  • Idle costs no CPU. Good for agents that wait a lot: Upstash bills only the CPU a box uses, RAM is free, and a request wakes a paused box.
  • Coding agents ready to drive. Claude Code, Codex and OpenCode come built in, with run and stream APIs, webhooks and scheduled prompts.
  • 1,000 boxes at once by default. Pay as You Go allows 1,000 boxes at once without a support request, in AWS us-east-1 close to US services.

Where boat fits

Azure and Upstash are both built for code that runs, sleeps and wakes up. If your agents do longer real work, like building containers, booting emulators or using a desktop, they need a whole machine. boat gives every agent a full VM with Docker, /dev/kvm, a desktop and coding agents built in.

Docker and /dev/kvm on every sandbox

Upstash boxes cannot run Docker, so the 50-agent scenario does not fit there. Azure has Docker only on images like azure-dev, and neither documents /dev/kvm for Android emulators or nested VMs.

A screen the agent can see

Both are headless. Upstash offers a headless Chromium over CDP, and on Azure you build a browser, a virtual display and streaming into your own image. boat streams a Linux desktop at 60fps with computer-use tools.

Keys that never enter the sandbox

Azure injects Copilot and Anthropic tokens into the sandbox at start, where a prompt-injected agent can read them. Upstash's header proxy is fixed at creation. boat's credentials proxy keeps keys outside and can switch accounts when credits run out.

Use boat when your agents need a whole computer: Docker, emulators, a desktop and a browser, SSH and raw TCP, with coding agents and a credentials proxy built in. Compare it one to one: boat vs Azure Container Apps Sandboxes and boat vs Upstash Box.

Questions people ask

Is Azure Container Apps Sandboxes cheaper than Upstash Box?

No. Upstash costs less in all five scenarios on this page: $21 against $68 for one coding agent on workdays, and $306 against $989 for sandboxes for your users. Upstash's 50-agent price does not fit, though, because it has no Docker inside.

Which is faster, Azure Container Apps Sandboxes or Upstash Box?

Neither has been measured on the same CPU test, so there is no fair answer yet. boat did 26.69 runs per second on the hpc-sandbox-benchmarks Node.js loop at 4 vCPU / 8 GB.

Can Azure Container Apps Sandboxes or Upstash Box run Docker?

On Azure, the azure-dev image ships Docker on systemd, while the default ubuntu image has only Buildah. Upstash does not offer Docker inside a box, since each box is itself a Docker container. boat runs Docker on every sandbox.

Can I SSH into them?

Upstash gives SSH through a gateway. Azure has no SSH and gives an interactive shell through the aca CLI, the SDK or the portal. Every boat sandbox has an SSH endpoint.

Which one keeps memory when it sleeps?

Azure suspends a sandbox with its memory and disk and resumes it in under a second with processes running. Upstash pauses an idle box and keeps its files. boat saves the disk every minute and on stop, and resuming boots the machine again.

Where do they run?

Azure Container Apps Sandboxes runs in 40 Azure regions, 9 of them in the EU. Upstash Box runs only in AWS us-east-1. boat runs in the EU, in Germany, Finland and France.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons