E2B vs Ona

E2B is a sandbox API: your code starts a small Firecracker microVM per agent job, and it can pause with its memory and wake on the next request. Ona, formerly Gitpod and now part of OpenAI, is a cloud dev environment platform for engineers and its Codex Agent. Since Ona Cloud and Core shut down on October 31, 2026, Ona sells only Enterprise, through sales, on runners in your own AWS or GCP account.

The companies and products

E2B

E2B calls itself the AI agent cloud: an API that gives each agent session its own isolated Linux machine.

Every E2B sandbox is a Firecracker microVM that boots from a snapshot, so it starts fast and can be paused and resumed with its memory. You build custom sandboxes from templates based on a Docker image, and drive them from Python or JavaScript SDKs. It is built for teams that run many short code, data or agent jobs. Its runtime is open source, and E2B Embed runs it on your own infrastructure.

Ona

Ona, formerly Gitpod, is a platform for cloud dev environments and background coding agents, and is now part of OpenAI.

Ona is a different kind of product from boat: a dev-environment platform, not a sandbox API. Each task or developer gets an isolated VM built from a Dev Container config. People open it in a browser IDE, VS Code or JetBrains, and Ona's Codex Agent can plan, code, test and open pull requests in it. Ona has a built-in web browser that its AI can drive, prebuilds and Enterprise warm pools. It is built for engineering teams who want the same governed environment for every developer and agent. Since Ona Cloud shut down on October 31, 2026, every customer runs it in their own AWS or GCP account on an Enterprise contract.

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. “20th cheapest of 365” means 19 of the other 364 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 workloadE2B: price rankOna: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
E2B fits a software factory through its self-serve API. On Ona each agent gets a VM, and the SDK on Enterprise starts them from code. boat adds /dev/kvm and no session cap once auto-stop is off.
20th cheapest of 365
$4,143 a month
334th of 365, with limits
$7,315 a month
5th cheapest of 365
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An assistant that runs all month: E2B Pro stops one run at 24 hours, and a pause and resume resets the clock. On Ona you set auto-stop to Never, because background work does not count as activity. On boat you turn auto-stop off on a paid plan (default 1 hour).
82nd of 361, with limits
$5,348 a month
147th of 361, with limits
$8,504 a month
6th cheapest of 361
$657 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
E2B is built for short code runs that start fast and pause with their memory. Ona is a dev environment platform, so it is a compromise here.
43rd cheapest of 336
$421 a month
326th of 336, with limits
$5,320 a month
189th of 336, 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
E2B hands sandboxes to your users through an API. Ona is built for your own engineers, and its per-user policy defaults to 10 running environments (admins can set 1 to 100).
33rd cheapest of 349
$2,354 a month
325th of 349, with limits
$5,988 a month
3rd cheapest of 349
$209 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
E2B's memory forks suit many short rollouts that branch from one state. Ona starts environments from a config, a prebuild or a warm pool, not from a copy of a running one.
5th cheapest of 349
$9,384 a month
277th of 349, with limits
$9,773 a month
39th of 349, with limits
$2,000 a month
Agent evals
250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month
87th cheapest of 359
$1,975 a month
332nd of 359, with limits
$5,768 a month
10th cheapest of 359
$200 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
E2B is a compromise for CI that needs nested virtualization: its docs list it as not supported. Ona starts each run from a prebuild or an Enterprise warm pool in about 10 seconds. boat has /dev/kvm and forks a warm machine from its last 1-minute snapshot; each fork counts as a start.
338th of 374, with limits
$1,429 a month
366th of 374, with limits
$5,461 a month
2nd cheapest of 374
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
Ona is a full cloud IDE with Dev Containers and prebuilds. E2B pauses and resumes once a day to pass its 24-hour cap. boat is a full VM you reach over SSH, HTTPS or a desktop.
208th of 371, with limits
$358 a month
371st of 371, with limits
$5,140 a month
19th cheapest of 371
$26 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
E2B has a Linux desktop for computer use, streamed over VNC. Ona has no full desktop, but its AI can drive a built-in browser inside the environment. boat streams a 60 fps desktop with Chrome.
34th cheapest of 367
$1,342 a month
355th of 367, with limits
$5,691 a month
7th cheapest of 367
$200 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
126th of 356, with limits
$746 a month
219th of 356, with limits
$5,346 a month
7th cheapest of 356
$200 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
62nd cheapest of 343
$554 a month
220th of 343, with limits
$5,468 a month
6th cheapest of 343
$90 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
226th of 327, with limits
$9,223 a month
261st of 327, with limits
$14,360 a month
73rd of 327, with limits
$1,800 a month
Parallel red teaming
200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month
17th cheapest of 351
$1,043 a month
150th of 351, with limits
$5,228 a month
3rd cheapest of 351
$200 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
Not ranked: misses a requirementNot ranked: misses a requirementNot ranked: misses a requirement
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Not ranked: misses a requirementNot ranked: misses a requirementNot ranked: misses a requirement

Key features

FeatureE2BOnaboat
What it isA sandbox API that gives each agent session its own Linux machineA cloud dev environment platform for engineers and its Codex AgentA sandbox API with full VMs and coding agents built in
IsolationFirecracker microVM with its own kernelIsolated VM with dedicated compute, built from a Dev Container configFull VM with its own kernel on hosts dedicated to boat (AMD Ryzen 7 9700X and Ryzen 9 9950X); vCPUs are shared
Signing up and driving it from codeSelf-serve Hobby ($0) and Pro plans; Python and JavaScript SDKsOna Cloud and Core shut down on October 31, 2026; Enterprise only, through sales, with Python, TypeScript and Go SDKsSelf-serve plans from $20 a month, and a 7-day trial with a card; API and SDK on every plan
CPU benchmark (V8 Web Tooling, 4 vCPU / 8 GB, StarSling run of 3 October 2026)11.08 runs/s, rank 7 of 15 (shared)Not in this benchmark28.06 runs/s, rank 2 of 15 (shared), on a Ryzen 9 9950X host
Docker and nested virtualizationDocker inside; docs list nested-virtualization runtimes as not supportedDocker and root inside the Dev Container; nested virtualization not documented on its VM classesDocker, root, systemd and /dev/kvm on every sandbox
Session lengthUp to 1 hour on Hobby, 24 hours on Pro; pausing resets the clockNo hard cap; stops after 30 idle minutes by default; background work does not count; can be set to NeverNo cap once auto-stop is off on a paid plan; auto-stop defaults to 1 hour, up to 30 days
Pause and resumeSaves memory and disk; resumes in about a second with processes running, and can wake on the next request; a paused sandbox costs nothingDisk persists across stops, on your cloud bill; Enterprise archives a stopped environment after 3 days by default (admins can set 1 to 30)Disk saved every minute and at each stop; no compute charge while stopped; disk kept at least 14 days; resume boots the machine again
ForkFork a running sandbox with its memory, up to 20 copies per callNo environment copy; create a project from an environment's config; Enterprise warm pools start a new environment in about 10 secondsFork a running sandbox from its last 1-minute disk snapshot
Desktop and computer useE2B Desktop sandbox with VNC streamingNo full desktop; a built-in browser its AI can drive; browser IDE, VS Code and JetBrainsBuilt-in desktop and Chrome at 1920x1080 and 60 fps, computer tools for agents and an embeddable stream
Team IDENone; you drive it from codeBrowser, VS Code and JetBrains IDEs with Dev Containers and prebuildsNone; you reach it over SSH, HTTPS or the desktop
Reaching the sandboxHTTPS URL per port, public by default unless you turn on a token; no public IP per sandboxHTTPS URL per port for you, your organization or everyone; SSH; no raw TCP or public IP documentedUp to 50 HTTPS URLs, token-gated by default; SSH; public IPv6 with raw ports; no dedicated IPv4
Coding agentsTemplates and guides for many agents, run through the command APIManaged Codex Agent started from chat, Slack, a pull request, a Linear issue or an automation; you install other agents yourselfSeven harnesses installed, among them Claude Code, Codex and OpenCode, with a prompt, steer and events API
Keeping API keys out of the sandboxSecrets injected into outbound HTTPS headers (private beta)Secrets injected as environment variables or files; OIDC for short-lived cloud credentialsOptional AI credentials proxy ($1 a day while on, plus $1 per 1,000 requests); with it on, real keys of supported providers stay outside the sandbox
GPUs, regions and your own cloudCPU only; US by default, EU and APAC by support; open-source runtime and your own cloud on EnterpriseGPU instance types such as an A10G; Enterprise runners in your own AWS or GCP accountNo GPUs; Germany, Finland and France; no US or Asia region
Every feature Battleships tracks (43)
FeatureE2BOnaboat
Full VM (own kernel)YesYesYes
Docker insideYesYesYes
Nested virtualizationNo documented wayNo documented wayYes
RootYesYesYes
SystemdYesNot publishedYes
Desktop GUIYesNo documented wayYes
BrowserYesYesYes
Computer-use APIYesNo documented wayYes
SSHYesYesYes
Persistent diskYesYesYes
Pause/resumeYesYesYes
Automatic snapshotsYesNo documented wayYes
Fork/cloneYesNo documented wayYes
Live fork (no pause)YesNo documented wayYes
Memory forkYesNo documented wayNo documented way
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesYesYes
Idle auto-stopYesYesNo documented way
Wake on requestYesNo documented wayNo documented way
HTTPS preview URLsYesYesYes
Raw TCP inboundNo documented wayNo documented wayYes
Public IPv4No documented wayNo documented wayNo documented way
Egress allowlistYesNo documented wayNo documented way
Secret proxyYesNo documented wayYes
Secret proxy for any APIYesNo documented wayYes
Preinstalled agentsYesYesYes
Agent harness APINo documented wayYesYes
MCP serverYesNo documented wayNo documented way
GPUNo documented wayYesNo documented way
WindowsNo documented wayNo documented wayNo documented way
Arm64No documented wayNo documented wayNo documented way
Self-hostingYesNo documented wayNo documented way
BYOCYesYesNo documented way
Open sourceYesNo documented wayNo documented way
Scoped API keysNot publishedNot publishedYes
Spend limitsYesYesYes
Usage per sandbox (API)No documented wayNo documented wayYes
Audit logsNot publishedNo documented wayNo documented way
SSONo documented wayYesNo documented way
SOC 2YesYesNo documented way
HIPAAYesNo documented wayNo documented way
EU data residencyYesYesNo documented way
Zero data retentionNot publishedNot publishedYes

Performance

E2B11.08 runs/s
OnaNot measured
boat28.06 runs/s

E2B and boat ran in StarSling's run of 3 October 2026 (run 37073680030), on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB: boat did 28.06 runs/s, second of 15, and E2B did 11.08, rank 7 (shared). Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Providers ran on different hardware in different regions. Ona is not in the public benchmarks we use, so we cannot say how it compares. This measures CPU work only, not start time.

V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Ona is not in the public benchmarks we use, so we cannot say which is faster.

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. Start limits, per-start fees and plan minimums are in the price, boat's included.

ScenarioE2B, a monthOna, 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
$202 · Pro$5,030 · Enterprise (AWS Marketplace 12-month contract) · with limits$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$368 · Pro · with limits$5,140 · Enterprise (AWS Marketplace 12-month contract) · 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
$2,773 · Pro$6,521 · Enterprise (AWS Marketplace 12-month contract) · 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
$1,395 · Pro+ (600 concurrent)$5,432 · Enterprise (AWS Marketplace 12-month contract) · 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
$2,797 · Pro++ (1,100 concurrent)$5,955 · Enterprise (AWS Marketplace 12-month contract) · with limits$8,800 · $2000/mo · with limits

E2B: E2B bills per second for the vCPU and RAM you set, idle time included, until you pause or kill the sandbox: $0.33 an hour for 4 vCPU / 8 GiB. A paused sandbox costs nothing. Hobby costs $0 with a one-time $100 credit. Pro costs $150 a month for higher limits, with no usage credit. Pro+ ($650) and Pro++ ($1,150) raise concurrency to 600 and 1,100 sandboxes.

Ona: Ona Cloud and Core shut down on October 31, 2026, so Ona prices here use its Enterprise listing on AWS Marketplace: a 12-month, $60,000 contract, plus compute on your own AWS bill. Real Enterprise prices are negotiated with sales.

Ona: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month; unused time does not carry over. A 4 vCPU / 8 GB sandbox costs $0.036 an hour, billed per second while it runs. A stopped sandbox has no compute charge, and boat keeps its disk for at least 14 days. Saved snapshots above the included count and the optional AI credentials proxy still charge while sandboxes are stopped. The $20 plan includes 200 starts a day; extra starts cost $0.03 to $0.07 each. A card is required, also for the 7-day trial.

Limits in those scenarios

E2B Pro stops one run at 24 hours, so the 24/7 scenario needs a daily pause and resume; its Pro disk is 20 GiB. No Ona scenario fits as published, because Ona sells only Enterprise, through sales; Ona publishes no Enterprise concurrency limit, so the table assumes 3 environments at once. For 1,000 short jobs at once, E2B Pro++ fits and queues bursts above 300 starts a minute. boat's $2,000 plan includes 90 starts a minute and 2,400 a day; extra starts cost $0.03 to $0.07, and starts above 270 a minute fail with 429. boat keeps a stopped disk at least 14 days, and a machine failure loses the writes after the last 1-minute snapshot.

ScenarioE2BOnaboat
One coding agent, workdays
  • disk beyond 20 GiB: price unknown
  • egress price not published
  • negotiated / enterprise price
  • different kind of product: CI runner
  • needs talk to sales: plan "Enterprise (AWS Marketplace 12-month contract)" is negotiated with sales
  • egress price not published
None for this scenario
One agent that never stops
  • Pro: sessions capped at 24 h
  • disk beyond 20 GiB: price unknown
  • egress price not published
  • negotiated / enterprise price
  • different kind of product: CI runner
  • needs talk to sales: plan "Enterprise (AWS Marketplace 12-month contract)" is negotiated with sales
  • egress price not published
None for this scenario
50 agents in parallel
  • egress price not published
  • Enterprise (AWS Marketplace 12-month contract): max 3 concurrent (not published; assumed like its other plans)
  • negotiated / enterprise price
  • different kind of product: CI runner
  • needs talk to sales: plan "Enterprise (AWS Marketplace 12-month contract)" is negotiated with sales
None for this scenario
Sandboxes for your users
  • egress price not published
  • Enterprise (AWS Marketplace 12-month contract): max 3 concurrent (not published; assumed like its other plans)
  • negotiated / enterprise price
  • different kind of product: CI runner
  • needs talk to sales: plan "Enterprise (AWS Marketplace 12-month contract)" is negotiated with sales
None for this scenario
1,000 short jobs at once
  • egress price not published
  • bursts above 300 starts/min are queued (a burst of 333 takes ~2 min to start)
  • Enterprise (AWS Marketplace 12-month contract): max 3 concurrent (not published; assumed like its other plans)
  • negotiated / enterprise price
  • different kind of product: CI runner
  • needs talk to sales: plan "Enterprise (AWS Marketplace 12-month contract)" is negotiated with sales
  • 2,400 starts/day included, paid above that (needs ~6,667)
  • 600 starts/hour included, paid above that (needs ~1,000)
  • starts above 90/min are paid, and starts above 270/min fail with 429

Which one should you use?

Use E2B when

your code runs many short agent or code jobs that pause between requests, branch from the same memory, or must run in the US or APAC.

  • Memory pause and wake on request. For short jobs that sleep between requests, a paused E2B sandbox comes back in about a second with its processes running, and costs nothing while paused.
  • A self-serve sandbox API. If your code starts the machines, E2B has a $0 Hobby plan, self-serve Pro and SDKs. Ona sells only Enterprise, through sales.
  • Huge bursts of short jobs. For thousands of short jobs at once, E2B Pro++ allows 1,100 sandboxes at a time, and memory forks suit rollouts.

Use Ona when

your engineers want a governed cloud IDE shared with a Codex agent, inside your own AWS or GCP account or with a GPU.

  • A full cloud IDE for your team. If engineers work in the same environments as their agents, Ona has browser, VS Code and JetBrains IDEs with prebuilds and warm pools.
  • Runs in your own cloud. If environments must run inside your own AWS or GCP account, Ona's Enterprise runners do that by default.
  • GPU environments. If your agents need a GPU, Ona's Enterprise runners can use GPU types, such as an A10G VM with 16 vCPU and 64 GB.

Where boat fits

If your code starts agents that work for hours, look at boat. E2B stops one run at 24 hours on Pro, and Ona is a team IDE sold through sales. boat gives each agent a full VM with an API on every plan, self-serve from $20 a month. boat is not the pick for GPUs, for runs outside the EU, or for memory pause.

A full machine with no session cap

On E2B a task longer than 24 hours needs a pause and resume, which your code sets up. On Ona an environment stops after 30 idle minutes unless auto-stop is set to Never. On a boat paid plan you turn auto-stop off (default 1 hour) and the sandbox runs until you stop it, billed at full rate.

Nested virtualization, a desktop and open ports

Android emulators need /dev/kvm: E2B's docs list it as not supported and Ona does not document it. Ona has a browser its AI drives but no full desktop. boat has /dev/kvm, a 60 fps desktop and up to 50 HTTPS URLs.

CPU and agents built in

In StarSling's run of 3 October 2026, boat did 28.06 V8 Web Tooling runs/s and E2B did 11.08; Ona is not in that benchmark. boat installs seven harnesses, and its optional credentials proxy ($1 a day while on, plus $1 per 1,000 requests) keeps real keys of supported providers outside the sandbox.

Use boat when your agents do hours of builds, Docker, emulators and browser work on a full VM, with no session cap once auto-stop is off, driven by an API on every plan. Compare it one to one: boat vs E2B and boat vs Ona.

boat's own limits
  • Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
  • Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
  • A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
  • Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
  • boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
  • Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
  • Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
  • Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source

Questions people ask

Is E2B cheaper than Ona?

In the scenarios we priced, yes: one coding agent on workdays is $202 a month on E2B and $5,030 on Ona, and 50 agents in parallel are $2,773 against $6,521. Ona's numbers use its Enterprise listing on AWS Marketplace, since Ona sells only Enterprise, and real quotes come from sales. boat is $20 and $317 for the same two.

Which is faster, E2B or Ona?

We cannot say: Ona is not in the public benchmarks we use. In StarSling's run of 3 October 2026, E2B did 11.08 V8 Web Tooling runs/s at 4 vCPU / 8 GB, and boat did 28.06 on a Ryzen 9 9950X host.

Can E2B and Ona run Docker?

Both run Docker inside. E2B's docs list nested virtualization as not supported, and Ona does not document it on its VM classes. boat exposes /dev/kvm for Android emulators and VMs.

Can an E2B or Ona sandbox run for days?

E2B stops one run after 24 hours on Pro; pausing and resuming resets the clock and keeps memory. Ona has no hard cap but stops after 30 idle minutes by default unless auto-stop is set to Never. boat has no session cap once auto-stop is off on a paid plan (default 1 hour).

Can I still sign up for Ona?

Not self-serve. Ona Cloud and Core shut down on October 31, 2026, and new customers buy Enterprise through sales. E2B and boat both have self-serve plans.

Is Ona the same as Gitpod?

Yes. Gitpod renamed itself Ona in 2025, and Ona is now part of OpenAI. Its managed agent is Codex.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons