Claude Managed Agents vs Azure Container Apps Sandboxes

Claude Managed Agents is a hosted agent: you send Claude a task, and Anthropic's harness runs it in a small container you never log into. Azure Container Apps Sandboxes gives you microVMs with their own kernel inside your Azure account, and you bring the agent and the code.

The companies and products

Claude Managed Agents

Claude Managed Agents is Anthropic's ready-made agent harness: Claude runs as an autonomous agent in a cloud sandbox that Anthropic manages, and you talk to it through an events API.

This is an agent platform, not a sandbox you rent. You define an agent (model, prompt, tools, MCP servers, skills) and an environment, then start sessions, send messages as events and stream back what Claude does; the harness handles tool calls, prompt caching and compaction. Each session gets its own Ubuntu container, or runs its tools on a worker you host yourself. It is built for teams that want Claude doing long tasks without building their own agent loop or sandbox.

Isolation: Each session gets its own isolated Linux container on Anthropic-managed infrastructure
Sandbox size: Ubuntu 24.04, x86_64, up to 8 GB memory and 10 GB disk; vCPU count not published
Models: Claude models only, through Anthropic's own harness
Billing: Model tokens at API rates, plus a session runtime fee that accrues only while a session is running
Self-hosted sandboxes: Tools can run on a worker in your own infrastructure while Anthropic keeps the orchestration
Data location: Workspace geo, which sets where data is stored and code runs, is US only today; inference can be global or US
Status: Beta, behind the managed-agents-2026-04-01 header; not eligible for Zero Data Retention or a HIPAA BAA

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.

Kind of product: A compute type inside Azure Container Apps, next to apps, jobs and dynamic sessions
Isolation: Each sandbox runs in its own secure boundary with its own kernel
Regions: 40 Azure regions, 9 of them in the EU
Sizes: Tiers from 0.25 cores / 0.5 GB to 4 cores / 8 GB; up to 16 vCPU / 32 GB by API
Quota: 500 concurrent active cores and 3,000 API requests a minute by default, raised by support request
Access: Microsoft Entra ID accounts only, with the Container Apps SandboxGroup Data Owner role
Compliance: Azure holds a SOC 2 Type 2 report for its cloud services; the scope list names which services it covers

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. “106th cheapest of 367” means 105 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	Claude Managed Agents: 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 Managed Agents gives Claude a container with up to 8 GB of memory and Docker only in limited availability; Azure can run Docker with the azure-dev image; boat adds SSH, /dev/kvm and a desktop on a full VM.	106th of 367, with limits $964 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 Managed Agents idles for free between messages but keeps sandbox state only 30 days after creation, and Azure bills every second a sandbox runs; boat keeps its disk as long as you keep the sandbox.	219th of 366, with limits $2,511 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 Azure fits short code runs well, since a sandbox suspends with its memory and resumes in under a second; Managed Agents bills runtime only while the agent works.	163rd of 345, with limits $756 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 gives each user sandbox public HTTPS routes per port, while a Managed Agents sandbox has no inbound ports at all; boat adds hosting on up to 50 ports and raw TCP.	231st of 361, with limits $823 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	252nd of 360, with limits $3,978 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	244th of 364, with limits $320 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 CI that builds Android apps or VM images needs /dev/kvm, which boat has and neither Managed Agents nor Azure documents.	227th of 377, with limits $96 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 offers SSH: Managed Agents is reached only through its sessions API and Azure through the aca CLI, SDK or portal; boat gives every sandbox SSH.	224th of 368, with limits $48 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 Both are headless, with no desktop or computer-use tool; boat streams a Linux desktop at 60fps in every sandbox.	127th of 369, with limits $288 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 Managed Agents ships headless Chromium with Playwright, while on Azure you install a browser yourself; boat shows Chromium on a live desktop you can take over.	126th of 367, with limits $288 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	127th of 346, with limits $390 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	155th of 338, with limits $4,798 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	179th of 360, with limits $160 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	Claude Managed Agents	Azure Container Apps Sandboxes	boat
What it is	A hosted Claude agent: Anthropic's harness runs Claude in a sandbox and you send it events	A compute type inside Azure Container Apps: microVMs you create, suspend and resume through an SDK	A sandbox platform: each agent gets its own full Linux machine, with coding agents built in
Isolation	Isolated Linux container per session	MicroVM per sandbox with its own kernel	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Machine size	Up to 8 GB memory and 10 GB disk; vCPU not published; not configurable	Tiers from 0.25 cores / 0.5 GB to 4 cores / 8 GB; up to 16 vCPU / 32 GB by API	Up to 16 vCPU / 32 GB on the $100 plan and above
Docker, systemd and /dev/kvm	Docker in limited availability; root, systemd and /dev/kvm not documented	Docker and systemd with the azure-dev image; default ubuntu image has only Buildah; nested virtualization not documented	Root, Docker, systemd and /dev/kvm on every sandbox, for Android emulators and VMs
Getting a shell	No shell or SSH; you reach the sandbox only through the sessions and events API	Interactive shell through the aca CLI, SDK or portal; no SSH	SSH, plus CLI and API exec
Inbound access	No inbound ports	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; dedicated IPv4 or IPv6
Desktop, browser and computer use	Headless Chromium with Playwright; no desktop or computer-use tool	Headless; no desktop or managed browser	Linux desktop streamed at 60fps, Chromium and computer-use tools preinstalled
Idle and wake	Idle session is checkpointed for free and resumes on the next message	Auto-suspend with memory after an idle timeout; traffic or a start command resumes it in under a second	Auto-stop timer you set; disk saved every minute and on stop; a stopped sandbox is started by API
How long files last	Sandbox state kept only 30 days after the sandbox is created	Kept until a lifecycle policy or you delete the stopped sandbox	The whole disk, for as long as you keep the sandbox
Fork	No fork or clone of a session or sandbox	Snapshot a running sandbox with its memory and create new sandboxes from it	Fork a running sandbox with its disk
Agents	Anthropic's harness with Claude models only, with steering, memory stores, multiagent threads and webhooks	Copilot CLI and Claude Code images, run through the exec API	Claude Code, Codex and five more preinstalled, driven from outside with a prompt, steer and events API
Keeping API keys out of the sandbox	Vault secrets live in the sandbox as placeholders and are swapped in at egress, per host	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; switch a credential to another account when credits run out
Outbound rules	Unrestricted, or limited to listed hosts plus optional package registries and MCP servers	Egress policy with allow, deny, rewrite and header rules by host, path and method; VNet integration	Open internet, no provider-side allowlist
Where it runs	US workspace geo only; self-hosted workers can run tools on your own machines	40 Azure regions, 9 of them in the EU	EU only (Germany, Finland, France), with zero data retention

Every feature Battleships tracks (43)

Feature	Claude Managed Agents	Azure Container Apps Sandboxes	boat
Full VM (own kernel)	No	Yes	Yes
Docker inside	Not published	Yes	Yes
Nested virtualization	No	No	Yes
Root	Not published	Yes	Yes
Systemd	Not published	Yes	Yes
Desktop GUI	No	No	Yes
Browser	Yes	No	Yes
Computer-use API	No	No	Yes
SSH	No	No	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	Yes	Yes	Yes
Automatic snapshots	Yes	Yes	Yes
Fork/clone	No	Yes	Yes
Live fork (no pause)	No	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	Yes	No
Wake on request	Yes	Yes	No
HTTPS preview URLs	No	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	Yes	No	Yes
MCP server	Yes	No	No
GPU	No	No	No
Windows	No	No	No
Arm64	No	No	No
Self-hosting	Yes	No	No
BYOC	Yes	No	No
Open source	No	No	No
Scoped API keys	Not published	Not published	Yes
Spend limits	Yes	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	No	Yes	No
EU data residency	No	Yes	Yes
Zero data retention	No	Not published	Yes

Performance

Claude Managed AgentsNot measured

Azure Container Apps SandboxesNot measured

boat26.69 runs/s

There is no comparable CPU measurement for either one: neither Claude Managed Agents nor Azure Container Apps Sandboxes was part of the hpc-sandbox-benchmarks run, and Anthropic does not publish how many vCPUs its sandbox gets. boat did 26.69 runs per second on the Node.js build-and-test loop at 4 vCPU / 8 GB. This page makes no speed claim between the three.

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

Scenario	Claude Managed Agents, 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	$13 · Claude API (pay-as-you-go, usage tiers) · with limits	$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	$53 · Claude API (pay-as-you-go, usage tiers) · with limits	$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	$634 · Claude API (pay-as-you-go, usage tiers) · with limits	$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	$360 · Claude API (pay-as-you-go, usage tiers) · 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	$796 · Claude API (pay-as-you-go, usage tiers) · with limits	$2,148 · Pay-as-you-go	$2,000 · $2000/mo · with limits

Claude Managed Agents: Managed Agents bills model tokens at API rates plus a flat session runtime fee, metered to the millisecond only while a session is running, including time waiting on the model. The tables show runtime only; tokens come on top and usually cost more.

Azure Container Apps Sandboxes: Azure bills per second on the Container Apps Consumption meters for the vCPU and memory of the sandbox's tier, idle time before auto-suspend included. There is no plan fee, and some regions such as West Europe and UK South charge more per second.

Azure Container Apps Sandboxes: 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

No scenario counts as a clean fit for Managed Agents: its sandbox size is not published beyond 8 GB of memory and 10 GB of disk, Docker is only in limited availability, and no concurrency cap is published for runs of 300 or 1,000 at once. Azure fits most scenarios, but it bills a running sandbox every second, so the always-on agent only gets close with a 3-year commitment, and its default quota of 500 active cores caps a fleet until support raises it. boat fits every scenario but the burst of 1,000 short jobs, where its plan queues starts above 90 a minute.

Scenario	Claude Managed Agents	Azure Container Apps Sandboxes	boat
One coding agent, workdays	adjacent product, not a like-for-like sandbox machine size not published different kind of product: agent-platform machine size per session not published	None that bite	None that bite
One agent that never stops	adjacent product, not a like-for-like sandbox machine size not published different kind of product: agent-platform machine size per session not published	3-year commitment	None that bite
50 agents in parallel	adjacent product, not a like-for-like sandbox not confirmed: Docker inside machine size not published different kind of product: agent-platform	None that bite	None that bite
Sandboxes for your users	adjacent product, not a like-for-like sandbox machine size not published different kind of product: agent-platform not confirmed: how many machines can run at once (you need 300; the typical published limit is 50)	None that bite	None that bite
1,000 short jobs at once	adjacent product, not a like-for-like sandbox machine size not published different kind of product: agent-platform not confirmed: how many machines can run at once (you need 1,000; the typical published limit is 50)	None that bite	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 Claude Managed Agents when

you want Claude itself to do long text and code tasks with no harness to build, idle time that costs nothing, and the option to run tools on your own workers.

No agent loop to build. Teams that want Claude doing long tasks get the harness, caching, compaction, memory and webhooks ready to use.
Idle time is free. Agents that wait long between messages pay runtime only while working, and wake from a checkpoint on the next message.
Tools on your own workers. Teams that must keep tool calls and files in-house can run them on self-hosted workers while Anthropic runs the agent.

Use Azure Container Apps Sandboxes when

your team is already on Azure and wants short stateful sandboxes for any code that suspend with their memory, wake on traffic, follow strict egress rules or run outside the EU.

Any code, not only Claude. Teams that bring their own agent or code get a microVM with its own kernel, sized up to 16 vCPU / 32 GB.
Memory suspend and snapshots. Stateful jobs can suspend with their memory, resume in under a second, and seed many new sandboxes from one snapshot.
Inside Azure, in 40 regions. Teams already on Azure get Entra ID, Azure billing, VNets and fine egress rules, in 40 regions.

Where boat fits

If your agents need to do real machine work, like Docker builds, Android emulators, a browser on a screen or a server you can open, both options leave gaps. Managed Agents keeps Claude in a small container you cannot log into, and Azure gives you a headless microVM you reach through its CLI. boat gives each agent a full VM with SSH, a desktop and agents built in.

A whole machine with its own kernel

Neither documents /dev/kvm, so Android emulators and nested VMs cannot start. Managed Agents also caps memory at 8 GB with Docker in limited availability, and Azure needs the azure-dev image for Docker.

A screen, SSH and ports you can open

Both are headless, so a computer-use agent has nothing to look at unless you build a display stack yourself. Managed Agents has no inbound ports or SSH, and Azure has HTTPS routes but no SSH or raw TCP.

Any agent, keys kept outside

Managed Agents runs only Claude through Anthropic's harness. Azure's Copilot and Claude images run through raw exec, with tokens injected into the sandbox where a prompt-injected agent can read them. boat drives seven agents from outside and keeps keys in a proxy.

Use boat when your agents need a whole computer: SSH, Docker, emulators, a desktop and browser, ports you can open, a disk that lasts, and Claude Code, Codex or other agents built in. Compare it one to one: boat vs Claude Managed Agents and boat vs Azure Container Apps Sandboxes.

Questions people ask

Is Claude Managed Agents cheaper than Azure Container Apps Sandboxes?

For runtime alone, Managed Agents costs less in every scenario here, for example $634 against $3,421 a month for 50 agents in parallel. But that leaves out model tokens, which usually cost more than the runtime, and its sandbox size is not published, so none of those scenarios is a clean fit. boat costs $317 a month for the same fleet.

Which is faster, Claude Managed Agents or Azure Container Apps Sandboxes?

Neither has been measured on the same CPU test, so there is no fair answer. boat did 26.69 runs per second on the Node.js build-and-test loop at 4 vCPU / 8 GB. On Managed Agents, much of a session is often spent waiting on the model rather than the CPU.

Can Claude Managed Agents or Azure Container Apps Sandboxes run Docker?

Managed Agents lists Docker as limited availability. On Azure, the azure-dev image ships Docker on systemd, while the default ubuntu image has only Buildah. boat runs Docker on every sandbox and also exposes /dev/kvm.

Can I run Claude Code on either one?

Not on Managed Agents, which runs Anthropic's own harness with Claude models. Azure has a Claude Code image that you run through its exec API, with the token injected into the sandbox. boat ships Claude Code, Codex and five other agents and drives them from outside.

Can I SSH into Claude Managed Agents or Azure Container Apps Sandboxes?

No. Managed Agents is reached only through its sessions and events API, and Azure gives a shell through the aca CLI, SDK or portal. Every boat sandbox has SSH, raw TCP and HTTPS on up to 50 ports.

Is boat SOC 2 compliant?

SOC 2 is in progress. We're open about where we stand: live status at status.ascii.dev and our data retention policy at docs.boat.dev/data-retention.

Try boat

Install the CLI, then run boat new.

7-day free trial