Fly.io Machines vs Claude Managed Agents

Fly.io Machines are fast-starting microVMs that boot your own image in 17 regions, so you build the sandbox and the agent loop yourself. Claude Managed Agents is Anthropic's hosted agent: you send a task as events, and Claude works in a small container that Anthropic runs for you.

The companies and products

Fly.io Machines

Fly.io is an app hosting platform, and Machines are the microVMs underneath it that you can also start and stop through a REST API.

A Fly Machine boots your Docker image as a Firecracker microVM on Fly's own servers, in one of 17 regions. You pick a shared or performance CPU preset, attach at most one Volume for data that must last, and Fly Proxy can stop, suspend and wake Machines as traffic comes and goes. It is built for teams that host web apps and services worldwide; it is not a sandbox product, so this page compares the parts that overlap with agent work.

Kind of product: App hosting platform; Machines are its VM building block with a REST API
Isolation: Firecracker microVMs with hardware virtualization, on Fly's own servers
Regions: 17 regions in North America, Europe, Asia, Oceania, South America and Africa
CPU classes: Shared vCPUs guarantee 6.25% of each core with a burst balance; performance vCPUs get the full core
Storage: Root file system is ephemeral; one Volume of up to 500GB per Machine for lasting data
Free trial: 2 Machine hours or 7 days, up to 10 Machines of 2 vCPU / 4GB that stop after 5 minutes
Compliance: Lists SOC 2 Type II; a HIPAA package with a pre-signed BAA is sold as an add-on

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

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. “92nd cheapest of 367” means 91 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	Fly.io Machines: price rank	Claude Managed Agents: price rank	bochka: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Fly gives a coding agent a microVM with root but a root disk that resets on restart, Managed Agents gives a container with up to 8 GB of memory, and bochka fits fully with Docker, /dev/kvm and a desktop.	92nd of 367, with limits $836 a month	106th of 367, with limits $964 a month	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Managed Agents sleeps idle sessions for free but keeps sandbox state only 30 days after creation; Fly keeps only what sits on one Volume; bochka keeps the whole disk.	125th of 366, with limits $816 a month	219th of 366, with limits $2,511 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 beat bochka for short bursts: Fly bills per second with no plan fee, and Managed Agents bills runtime only while the agent is working.	75th of 345, with limits $94 a month	163rd of 345, with limits $756 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 Fly can host one VM per user with public HTTPS, while a Managed Agents sandbox has no inbound ports; bochka gives each sandbox HTTPS URLs on up to 50 ports.	69th of 361, with limits $600 a month	231st of 361, with limits $823 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 Fly ranks well above Managed Agents here thanks to per-second billing with no plan fee, but Fly's API creates about one Machine per second per app.	48th of 360, with limits $2,838 a month	252nd of 360, with limits $3,978 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	117th of 364, with limits $457 a month	244th of 364, with limits $320 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 keeps the CPU busy, which drains a shared Fly vCPU's burst balance, and Managed Agents lists Docker only in limited availability; bochka has Docker and /dev/kvm ready.	152nd of 377, with limits $288 a month	227th of 377, with limits $96 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB	118th of 368, with limits $53 a month	224th of 368, with limits $48 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 Neither has a desktop or computer use built in (Managed Agents has headless Chromium with Playwright); bochka streams a Linux desktop at 60fps.	95th of 369, with limits $173 a month	127th of 369, with limits $288 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	160th of 367, with limits $90 a month	126th of 367, with limits $288 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	161st of 346, with limits $67 a month	127th of 346, with limits $390 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 Fly is the strongest of the three here: it spreads scrapers across 17 regions and pays only for the seconds they run.	44th of 338, with limits $1,232 a month	155th of 338, with limits $4,798 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	118th of 360, with limits $63 a month	179th of 360, with limits $160 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	Fly.io Machines	Claude Managed Agents	bochka
What it is	App hosting platform; Machines are microVMs you boot from your own image through a REST API	A hosted Claude agent: Anthropic's harness runs Claude in a sandbox and you send it events	Agent sandbox: a full VM per agent, with coding agents built in
Isolation	Firecracker microVM with its own kernel	Isolated Linux container per session	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Machine size	Shared or performance CPU presets you choose; one Volume of up to 500GB	Up to 8 GB memory and 10 GB disk; vCPU count not published; not configurable	Up to 16 vCPU / 32 GB on the $100 plan and above
Docker, systemd and /dev/kvm	Root and Docker you install yourself; Fly's own init, no systemd; no /dev/kvm	Docker in limited availability; root, systemd and /dev/kvm not documented	Root, Docker, systemd and /dev/kvm on every machine
Files after a stop	Root file system is ephemeral; lasting data goes on one Volume, billed for its full size all month	Checkpointed when a session goes idle; state kept only 30 days after the sandbox is created	The whole disk, saved every minute and on stop, for as long as you keep the sandbox
Pause and wake	Fly Proxy stops or suspends idle Machines and wakes them on a request; suspend keeps memory up to 2GB	An idle session resumes from its checkpoint on the next message, and idle time is not billed	Started and stopped through the API; resume reboots from disk
Fork	Clone copies a Machine's config; a cloned Volume starts empty	No fork or clone of a session or sandbox	Fork a running sandbox, disk included
Agent loop	None built in; you install agents and write the code that drives them	Anthropic's harness with Claude models, caching, compaction, memory stores and webhooks	Claude Code, Codex and five more preinstalled, driven from outside with a prompt, steer and events API
Browser and desktop	None built in; you add a browser and desktop to your own image	Headless Chromium with Playwright; no desktop or computer-use tool	60fps Linux desktop with Chromium, computer use and browser control
Inbound access	Public HTTPS and TCP through Fly Proxy, Anycast IPs, custom domains, private network	No inbound ports or SSH; reached only through the sessions and events API	HTTPS URLs on up to 50 ports, token-protected; raw TCP; SSH
Keeping API keys out of the sandbox	Secrets arrive as environment variables; an open-source tokenizer proxy you deploy yourself	Vault secrets sit in the sandbox as placeholders and are swapped in at egress, per host	Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Outbound rules	Network policies allow chosen ports and protocols and deny the rest	Unrestricted, or limited to listed hosts plus package registries and MCP servers	Open internet, no provider-side allowlist
Models and agents	Any, since you bring your own code	Claude models only, through Anthropic's harness	Claude Code, Codex, OpenCode and more, with any model provider
Where it runs	17 regions on six continents	US workspace geo only; inference can be global or US	EU only: Germany, Finland, France

Every feature Battleships tracks (43)

Feature	Fly.io Machines	Claude Managed Agents	bochka
Full VM (own kernel)	Yes	No	Yes
Docker inside	Yes	Not published	Yes
Nested virtualization	No	No	Yes
Root	Yes	Not published	Yes
Systemd	No	Not published	Yes
Desktop GUI	No	No	Yes
Browser	No	Yes	Yes
Computer-use API	No	No	Yes
SSH	Yes	No	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	Yes	Yes	Yes
Automatic snapshots	Yes	Yes	Yes
Fork/clone	Yes	No	Yes
Live fork (no pause)	Yes	No	Yes
Memory fork	No	No	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	No	Yes
Raw TCP inbound	Yes	No	Yes
Public IPv4	Yes	No	No
Egress allowlist	Yes	Yes	No
Secret proxy	No	Yes	Yes
Secret proxy for any API	No	Yes	Yes
Preinstalled agents	No	Yes	Yes
Agent harness API	No	Yes	Yes
MCP server	Yes	Yes	No
GPU	No	No	No
Windows	No	No	No
Arm64	No	No	No
Self-hosting	No	Yes	No
BYOC	No	Yes	No
Open source	Yes	No	No
Scoped API keys	Not published	Not published	Yes
Spend limits	No	Yes	Yes
Usage per sandbox (API)	No	Yes	Yes
Audit logs	Not published	Not published	No
SSO	No	Yes	No
SOC 2	Yes	Yes	No
HIPAA	Yes	No	No
EU data residency	Yes	No	Yes
Zero data retention	Not published	No	Yes

Performance

Fly.io MachinesNot measured

Claude Managed AgentsNot measured

bochka26.69 runs/s

There is no comparable measurement for either: neither Fly.io Machines nor Claude Managed Agents was part of the public StarSling run, where bochka did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB. Fly's results would depend on the CPU class, since shared vCPUs guarantee only 6.25% of a core, and Anthropic does not publish how many vCPUs a Managed Agents sandbox gets.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Fly.io Machines and Claude Managed Agents 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	Fly.io Machines, a month	Claude Managed Agents, 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	$15 · Pay As You Go · with limits	$13 · Claude API (pay-as-you-go, usage tiers) · with limits	$20 · $20/mo
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$36 · Pay As You Go · with limits	$53 · Claude API (pay-as-you-go, usage tiers) · 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	$487 · Pay As You Go · with limits	$634 · Claude API (pay-as-you-go, usage tiers) · 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	$110 · Pay As You Go · with limits	$360 · Claude API (pay-as-you-go, usage tiers) · with limits	$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	$232 · Pay As You Go · with limits	$796 · Claude API (pay-as-you-go, usage tiers) · with limits	$2,000 · $2000/mo · with limits

Fly.io Machines: Fly bills each Machine per second while it runs, by CPU preset and memory, with no plan fee; Volumes are billed for their full size all month. The figures use Fly's lowest rate: shared vCPUs bought in 1-year reservation blocks.

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

Claude Managed Agents: Plans start at $20 a month, and the whole fee is usage credit spent per second while a sandbox runs. A stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

Neither fits any scenario cleanly. Fly's lowest figures need a 1-year reservation and use shared vCPUs that guarantee 6.25% of each core, so long builds get throttled, and its API creates about one Machine per second per app. Managed Agents caps a sandbox at 8 GB of memory and 10 GB of disk, does not publish its vCPU count, and has Docker only in limited availability. On bochka the 1,000-job burst is queued even on the $2,000 plan, at 90 starts per minute and 2,400 a day.

Scenario	Fly.io Machines	Claude Managed Agents	bochka
One coding agent, workdays	different kind of product: app platform 1-year commitment burstable CPU: 6.25% of each vCPU guaranteed, throttled above that	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
One agent that never stops	different kind of product: app platform 1-year commitment burstable CPU: 6.25% of each vCPU guaranteed, throttled above that	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
50 agents in parallel	different kind of product: app platform 1-year commitment burstable CPU: 6.25% of each vCPU guaranteed, throttled above that	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
Sandboxes for your users	different kind of product: app platform 1-year commitment burstable CPU: 6.25% of each vCPU guaranteed, throttled above that	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
1,000 short jobs at once	different kind of product: app platform 1-year commitment burstable CPU: 6.25% of each vCPU guaranteed, throttled above that	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)	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 Fly.io Machines when

you want to build your own sandbox from your own image, host apps around it, and run near users in 17 regions.

17 regions worldwide. Useful when agents or users sit outside Europe and the US: Fly runs Machines in 17 regions, from Sydney to Johannesburg.
Host the whole app next to it. Useful if you host products too: public HTTPS and TCP, Anycast IPs, custom domains and a private network around each Machine.
Any image, any agent. Useful if you want full control: Fly boots your own Docker image, so you pick the agent, the model and every tool.

Use Claude Managed Agents when

you want Claude itself doing long text and code tasks with no harness to build, and idle time that costs nothing.

No agent loop to build. Teams that want Claude doing long tasks get the harness, caching, compaction, memory and webhooks ready to use.
Idle sessions sleep for free. Agents that wait long between messages pay runtime only while working, and resume on the next message with files kept.
Host allowlists and your own workers. Teams with strict network rules can limit sandboxes to listed hosts, or run every tool call on their own infrastructure.

Where bochka fits

Fly.io Machines give you a VM but leave the sandbox and the agent to you, and Claude Managed Agents gives you the agent but only a small container you cannot open. If what you are running is coding or computer-use agents that need a real machine, bochka sits in between: a full VM with agents built in, a disk that lasts and ports you can open.

A full machine that keeps its disk

A Fly Machine resets its root disk on restart unless you pay for a Volume all month, and a Managed Agents container caps out at 8 GB with state that expires after 30 days. bochka keeps the whole disk, saved every minute, and a stopped sandbox costs nothing.

Docker, systemd and /dev/kvm ready

Fly has no systemd or /dev/kvm, and Managed Agents lists Docker only in limited availability, so emulators and nested VMs have nowhere to run. Every bochka machine has root, Docker, systemd and /dev/kvm.

Agents and a desktop you can open

On Fly you build the image, desktop and agent driver yourself; on Managed Agents you get only Claude and no inbound ports. bochka ships Claude Code, Codex and more, a 60fps desktop, and HTTPS on up to 50 ports.

Use bochka when your agents need a real machine: Docker, emulators, a desktop and browser, ports you can open, a disk that lasts, and the choice of Claude Code, Codex or other agents. Compare it one to one: bochka vs Fly.io Machines and bochka vs Claude Managed Agents.

Questions people ask

Is Fly.io Machines cheaper than Claude Managed Agents?

For runtime, Fly costs less in four of the five scenarios, using its 1-year reserved shared vCPUs: for example 50 agents in parallel are $487 a month on Fly against $634 on Managed Agents, and bochka is $317. For one agent on workdays Managed Agents is lowest, and its model tokens always come on top.

Which is faster, Fly.io Machines or Claude Managed Agents?

Neither has a published CPU measurement, so there is no fair answer. Fly's shared vCPUs guarantee only 6.25% of a core and throttle sustained load, and Managed Agents does not publish its vCPU count. bochka measured 26.69 runs per second at 4 vCPU / 8 GB.

Can I run Docker on Fly.io Machines or Claude Managed Agents?

On Fly you can install and run Docker yourself, since a Machine is a microVM with root, but there is no /dev/kvm for nested VMs. Managed Agents lists Docker only as limited availability. bochka has Docker, systemd and /dev/kvm on every machine.

Can I run Claude Code on either?

On Fly you can, by installing it in your own image and writing the code that drives it. Managed Agents runs Anthropic's own harness, not Claude Code. bochka has Claude Code, Codex and five other agents preinstalled.

Do they keep files when the agent stops?

A Fly Machine keeps only what is on its one Volume, since its root file system is ephemeral. Managed Agents checkpoints an idle session but keeps sandbox state only 30 days after creation. bochka keeps the whole disk, saved every minute, until you delete the sandbox.

Where does my data run?

Fly runs Machines in 17 regions worldwide. Managed Agents stores data and runs code in the US workspace geo only. bochka runs only in the EU (Germany, Finland and France), with EU data residency.

Try bochka

Install the CLI, then run bochka new.

Product preview