E2B vs Together Code Sandbox

E2B is a self-serve API for microVMs that pause with their memory, wake on the next request and fork while running. Together Code Sandbox runs VMs started from Docker-image snapshots, and saves disk and memory when a sandbox ends. Together must enable it for your organization.

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.

Together Code Sandbox

Together AI is a cloud for running and training AI models, and Code Sandbox is its product for running code in isolated VMs.

You build a snapshot from a Docker image or Dockerfile on Together's builder, then start sandboxes from it and run commands and file operations through the together-sandbox SDK or CLI. When a sandbox ends you can save its disk, and its memory too, as a new snapshot to start more sandboxes from. It is aimed at model-generated code, agent tool calls and reinforcement learning rollouts, and Together must enable it for your organization. The pricing page also lists Code Interpreter at $0.03 per 60-minute session.

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 rankTogether Code Sandbox: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
E2B runs Docker and root inside its sandboxes. Together runs commands as user 1000 by default and root per exec on request; its docs do not describe Docker inside a sandbox. boat adds /dev/kvm.
20th cheapest of 365
$4,143 a month
67th of 365, with limits
$528 a month
5th cheapest of 365
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An assistant that lives on its machine all month: E2B Pro stops one run at 24 hours, and a pause and resume resets the clock. A Together sandbox runs until you terminate it or its ttl ends, so your backend starts and stops it. On boat you turn auto-stop off on a paid plan (default 1 hour).
82nd of 361, with limits
$5,348 a month
107th of 361, with limits
$1,095 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
Both run short code through an API. E2B starts fast and pauses between requests, and wakes on the next one. Together runs execs in a sandbox and has no idle detection or wake on request.
43rd cheapest of 336
$421 a month
318th of 336, with limits
$2,190 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 wakes a paused sandbox on the next request. On Together every port URL is open to everyone by default, unless you set an experimental access policy. boat's HTTPS URLs are token-protected by default.
33rd cheapest of 349
$2,354 a month
231st of 349, with limits
$900 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
Both suit rollouts that branch from one warm state. E2B forks a running sandbox with its memory. Together saves a sandbox with its memory when it ends and starts many copies from that snapshot, once Together enables the product.
5th cheapest of 349
$9,384 a month
309th of 349, with limits
$21,900 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
260th of 359, with limits
$450 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
CI that builds Android apps or VM images needs nested virtualization. E2B's docs list it as not supported, and Together does not document it. boat exposes /dev/kvm.
338th of 374, with limits
$1,429 a month
253rd of 374, with limits
$180 a month
2nd cheapest of 374
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
208th of 371, with limits
$358 a month
226th of 371, with limits
$22 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. On Together you build a desktop and browser into your image yourself. boat streams its desktop at 60 fps.
34th cheapest of 367
$1,342 a month
105th of 367, with limits
$600 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
E2B has a browser and desktop. On Together you install a browser in your own image.
126th of 356, with limits
$746 a month
195th of 356, with limits
$900 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
181st of 343, with limits
$180 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
126th of 327, with limits
$3,600 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
95th of 351, with limits
$150 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

FeatureE2BTogether Code Sandboxboat
Getting startedSelf-serve sign-up, with a $0 Hobby plan and a one-time $100 creditThe SDK and CLI must be enabled for your organization by TogetherSign up with a card (7-day trial), then start a sandbox from the API, CLI or dashboard
IsolationFirecracker microVM with its own kernelA VM per sandbox on Together's infrastructureFull VM with its own kernel on hosts dedicated to boat (AMD Ryzen 7 9700X and Ryzen 9 9950X); vCPUs are shared
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
List price, 4 vCPU / 8 GB running$0.33 an hour, billed per second; $0 while pausedAbout $0.30 an hour ($0.0446 per vCPU-hour + $0.0149 per GiB-hour); billing granularity not published$0.036 an hour, billed per second, from a $20 monthly plan (all of it VM time for that month)
Machine size1 to 8 vCPU and 1 to 8 GiB RAM self-serve, more on request0.1 to 16 cores, 1 to 8 GB per core; disk size not configurable2, 4, 8 or 16 vCPU at 2 GB per vCPU; disk 51 to 251 GB by size; 16 vCPU needs the $100 plan
Session length1 hour on Hobby, 24 hours on Pro; pausing resets the clockRuns until you terminate it or its ttl ends; ttl counts from creationNo cap once auto-stop is off on a paid plan; auto-stop defaults to 1 hour
Saving statePause with memory and disk; resume in about a second with processes running; a paused sandbox costs nothingEnd a sandbox with a snapshot of its disk, or disk and memory, and start new ones from it with processes runningDisk 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 callThe parent stops first, then you start many sandboxes from its snapshot, with memory if you askFork a running sandbox from its last 1-minute disk snapshot; the original keeps running
Idle and wakeOptional pause after a timeout, and wake on the next HTTP request or SDK callNo idle detection and no wake on requestAuto-stop timer from creation or resume, not an idle check; started again by API
Docker, root and systemdDocker, root and systemd insideCommands run as user 1000 by default, root per exec on request; Docker inside a sandbox not documentedDocker, systemd and root on every sandbox
Nested virtualizationDocs list nested-virtualization runtimes as not supportedNot documentedYes, /dev/kvm for Android emulators and VMs
Reaching the sandboxHTTPS URL per port, public unless you turn on a token; no public IP per sandboxA URL per port, open to everyone by default; an experimental policy limits access by IP or requires a tokenUp to 50 HTTPS URLs, token-gated by default; SSH; public IPv6; no dedicated IPv4
Desktop and browserE2B Desktop sandbox with VNC streamingNo built-in desktop or stream; install a browser or virtual display in your own imageBuilt-in desktop and Chrome at 1920x1080 and 60 fps, with computer tools for agents
Keeping API keys out of the sandboxSecrets injected into outbound HTTPS headers (private beta)No credentials proxy documentedOptional AI credentials proxy ($1 a day while on, plus $1 per 1,000 requests); switch a credential to another account when credits run out
Regions and self-hostingUS by default, EU and APAC enabled by support; open-source runtime and your own cloud on EnterpriseRegions not published; SDKs and CLI are MIT-licensed, the platform is not; no self-hostingGermany, Finland and France; you cannot pick one; no self-hosting
Every feature Battleships tracks (43)
FeatureE2BTogether Code Sandboxboat
Full VM (own kernel)YesYesYes
Docker insideYesNot publishedYes
Nested virtualizationNo documented wayNo documented wayYes
RootYesYesYes
SystemdYesNot publishedYes
Desktop GUIYesNot publishedYes
BrowserYesNot publishedYes
Computer-use APIYesNot publishedYes
SSHYesNo documented wayYes
Persistent diskYesWith your own setupYes
Pause/resumeYesYesYes
Automatic snapshotsYesNo documented wayYes
Fork/cloneYesYesYes
Live fork (no pause)YesNo documented wayYes
Memory forkYesYesNo documented way
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesYesYes
Idle auto-stopYesNo documented wayNo 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 agentsYesNo documented wayYes
Agent harness APINo documented wayNo documented wayYes
MCP serverYesYesNo documented way
GPUNo documented wayNo documented wayNo documented way
WindowsNo documented wayNo documented wayNo documented way
Arm64No documented wayNo documented wayNo documented way
Self-hostingYesNo documented wayNo documented way
BYOCYesNo documented wayNo documented way
Open sourceYesNo documented wayNo documented way
Scoped API keysNot publishedNot publishedYes
Spend limitsYesYesYes
Usage per sandbox (API)No documented wayYesYes
Audit logsNot publishedNot publishedNo documented way
SSONo documented wayYesNo documented way
SOC 2YesYesNo documented way
HIPAAYesNo documented wayNo documented way
EU data residencyYesNot publishedNo documented way
Zero data retentionNot publishedNot publishedYes

Performance

E2B11.08 runs/s
Together Code SandboxNot 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. Together Code Sandbox is not in the public benchmarks we use, so we cannot say how it compares.

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. Together Code Sandbox 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 monthTogether Code Sandbox, 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 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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$22 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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$264 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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)$900 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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)$6,000 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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.

Together Code Sandbox: Together lists Code Sandbox at $0.0446 per vCPU-hour and $0.0149 per GiB-hour, about $0.30 an hour at 4 vCPU / 8 GB, from prepaid credits. Your organization must have it enabled first. Billing granularity, snapshot storage and egress prices are not published. The pricing page also lists Code Interpreter at $0.03 per 60-minute session; the scenario table uses that line because Code Sandbox needs enablement.

Together Code Sandbox: 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.

Limits in those scenarios

E2B Pro stops one run at 24 hours, so the 24/7 scenario needs a daily pause and resume; Pro includes 20 GiB of disk. The scenario table's Together column uses the Code Interpreter line on Together's pricing page, because Code Sandbox needs Together to enable it; Code Interpreter's machine size is not published, so it fits no scenario. Together publishes no concurrency or start limits for Code Sandbox. For 1,000 short jobs at once, E2B Pro++ fits and queues starts above 300 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.

ScenarioE2BTogether Code Sandboxboat
One coding agent, workdays
  • disk beyond 20 GiB: price unknown
  • egress price not published
  • Together pay-as-you-go (prepaid credits; Code Interpreter only): sessions capped at 1 h
  • not confirmed: persistent disk
  • machine size not published
  • different kind of product: code interpreter
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
  • Together pay-as-you-go (prepaid credits; Code Interpreter only): sessions capped at 1 h
  • not confirmed: persistent disk
  • machine size not published
  • different kind of product: code interpreter
None for this scenario
50 agents in parallel
  • egress price not published
  • Together pay-as-you-go (prepaid credits; Code Interpreter only): sessions capped at 1 h
  • not confirmed: persistent disk
  • machine size not published
  • different kind of product: code interpreter
None for this scenario
Sandboxes for your users
  • egress price not published
  • machine size not published
  • different kind of product: code interpreter
  • machine size per session not published
  • egress price not published
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)
  • machine size not published
  • different kind of product: code interpreter
  • machine size per session not published
  • egress price not published
  • 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

you run many short jobs that pause between requests, need to fork running sandboxes with their memory, want to start self-serve today, or must run in the US or APAC.

  • Pause, wake and fork while running. For short jobs that sleep between requests: a paused sandbox wakes on the next call in about a second, processes intact, and costs nothing while paused.
  • Self-serve today, in more places. Anyone can sign up and start sandboxes now, in the US, EU or APAC, with outbound allow and deny lists.
  • Open source and your own cloud. Its runtime is Apache-2.0, E2B Embed runs it on your machines, and Enterprise customers can run it in their own AWS, GCP or Azure account.

Use Together Code Sandbox when

you already run models on Together and want light sandboxes, from a tenth of a core, that you can save with their memory and branch from.

  • Sandboxes next to your models. Handy if you already run inference or fine-tuning on Together: sandboxes and models share one account.
  • Very small and large machines. Sandboxes go from a tenth of a core up to 16 cores, priced per vCPU-hour and GiB-hour, which suits many light jobs or a few heavy ones.
  • Memory snapshots to branch from. Save a sandbox with its memory when it ends, then start many copies that come back with their processes running.

Where boat fits

E2B and Together are both built around short or snapshot-based runs. If your agents work for hours, build with Docker and emulators, use a desktop or serve apps to other people, boat gives each one a full machine that you can start today. boat has no memory snapshots and caps starts per plan.

A whole machine, with KVM

E2B's docs list nested virtualization as not supported, and Together does not document it or Docker inside a sandbox. boat has Docker, systemd, root, SSH and /dev/kvm on every sandbox.

No session cap once auto-stop is off

E2B stops one run after 24 hours on Pro, so your code pauses and resumes long tasks. A Together sandbox runs until its ttl ends, and your backend manages it. On boat you turn auto-stop off on a paid plan. In StarSling's run of 3 October 2026, boat did 28.06 V8 Web Tooling runs/s and E2B 11.08.

Agents, desktop and private hosting built in

On E2B and Together you run the agent harness through execs yourself. Together has no built-in desktop and leaves port URLs open by default. boat ships seven coding agents you drive from outside, a 60 fps desktop, an optional credentials proxy and token-protected HTTPS on 50 ports.

Use boat when your agents do hours of installs, builds, Docker, emulators and browser work, and serve apps to other people, on a full machine with the agents built in. Compare it one to one: boat vs E2B and boat vs Together Code Sandbox.

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 Together Code Sandbox?

At Together's Code Sandbox list rates, compute only, Together costs less: one agent on workdays is about $52 a month against $202 on E2B, 50 agents in parallel $2,619 against $2,773, and 1,000 short jobs at once $1,488 against $2,797. Code Sandbox must be enabled by Together, and its billing granularity is not published. boat is $20 and $317 for the first two; 1,000 jobs at once exceed boat's start limits.

Which is faster, E2B or Together Code Sandbox?

We cannot say: Together is not in StarSling's CPU benchmark. 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 Together Code Sandbox run Docker?

E2B runs Docker inside its sandboxes. Together builds sandboxes from Docker images, but its docs do not describe Docker inside a sandbox. E2B's docs list nested virtualization as not supported, and Together does not document it. boat has Docker and /dev/kvm on every sandbox.

Which one can keep a sandbox's memory?

Both. E2B pauses a running sandbox and resumes it in about a second, even on the next request. Together saves disk and memory when a sandbox ends, and new sandboxes start from that snapshot with processes running. boat saves the disk only, so a resume is like a reboot.

Can I sign up for Together Code Sandbox today?

The SDK and CLI must be enabled for your organization, so you ask Together for access. E2B and boat are both self-serve; boat needs a card, also for its 7-day trial.

Is boat SOC 2 compliant?

SOC 2 is in progress, so there is no SOC 2 report today. E2B has a SOC 2 Type II report, and Together's trust center lists a SOC 2 Type 2 report. boat's live status is at status.ascii.dev and its data retention policy is at docs.boat.dev/data-retention.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons