CodeSandbox SDK vs Google Agent Runtime
CodeSandbox SDK gives each sandbox a Firecracker VM with root and Docker that hibernates with its memory and wakes on the next HTTP request. Google Agent Runtime hosts your agent code on Google Cloud and runs its sandboxes as an unprivileged user in a locked container, with no Docker, inside your own project and network.
The companies and products
CodeSandbox SDK
CodeSandbox SDK is an API from CodeSandbox, now a Together AI company, that starts sandboxed development VMs on the same infrastructure as the CodeSandbox editor.
Each sandbox is a Firecracker microVM built from a template or any Dockerfile. When it goes idle it hibernates with a memory snapshot, and it resumes or forks from that snapshot in seconds. You drive it from a TypeScript SDK through terminals, commands, files and HTTPS hosts. Together's docs now call it the legacy offering and point new users to its successor, the together-sandbox SDK.
Google Agent Runtime
Google Agent Runtime is the agent hosting part of Gemini Enterprise Agent Platform on Google Cloud, renamed from Vertex AI Agent Engine in April 2026.
It is a hyperscaler service, not a sandbox company. Agent Runtime deploys agents you build with ADK, LangGraph, LangChain, AG2 or LlamaIndex and bills them only while they work on a turn. Next to it, Agent Sandbox gives those agents a place to run code: a Code Execution sandbox, a shell or custom container sandbox, and a Computer Use browser. All of them run as secure containers inside your Google Cloud project.
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. “46th cheapest of 345” means 45 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 workload | CodeSandbox SDK: price rank | Google Agent Runtime: price rank | bochka: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month CodeSandbox SDK runs Docker with root and Google's sandboxes do not, so builds and compose stacks fit CodeSandbox better; bochka adds SSH, systemd and /dev/kvm for emulators. | 178th of 367, with limits $1,939 a month | 295th of 367, with limits $5,801 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Google fits an always-on assistant better here, but its sandboxes are deleted after a 7-day TTL; a bochka VM has no session cap on paid plans. | 215th of 366, with limits $2,478 a month | 28th cheapest of 366 $7,519 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 suit short code runs: CodeSandbox SDK wakes hibernated VMs with their memory, and Google's Code Execution sandbox is a ready Python interpreter with no network. | 46th cheapest of 345 $642 a month | 254th of 345, with limits $275 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 CodeSandbox SDK gives each user an HTTPS host that wakes on request but caps Scale at 250 VMs at once; Google has no public URL; bochka serves HTTPS on up to 50 ports per sandbox. | 140th of 361, with limits $1,707 a month | 280th of 361, with limits $1,916 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 Both can branch many rollouts from one memory snapshot, CodeSandbox SDK by forking a running or hibernated VM and Google by starting sandboxes from one snapshot. | 348th of 360, with limits $3,861 a month | 128th of 360, with limits $8,240 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 | 64th cheapest of 364 $1,335 a month | 79th cheapest of 364 $2,060 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 jobs that build containers need Docker, which CodeSandbox SDK has and Google's unprivileged sandboxes do not; bochka also has /dev/kvm for Android builds. | 92nd cheapest of 377 $860 a month | 98th cheapest of 377 $989 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 310th of 368, with limits $240 a month | 311th of 368, with limits $241 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 Google gives you a browser with a VNC view and a click and type API, CodeSandbox SDK has no desktop, and bochka streams a full 60fps desktop with Chromium. | 206th of 369, with limits $691 a month | 283rd of 369, with limits $1,648 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 Google ships a real Chromium you drive over CDP, while on CodeSandbox SDK you start from a headless Chromium template; bochka has Chromium on a desktop in every sandbox. | 251st of 367, with limits $443 a month | 102nd of 367, with limits $824 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 | 281st of 346, with limits $508 a month | 53rd cheapest of 346 $515 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 | 193rd of 338, with limits $7,390 a month | 210th of 338, with limits $8,240 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 | 240th of 360, with limits $326 a month | 260th of 360, with limits $412 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 | CodeSandbox SDK | Google Agent Runtime | bochka |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | Secure container sandboxing inside Google Cloud | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Root and Docker | Root and Docker; built from any Dockerfile | Runs as appuser with no sudo; images must not need root; no Docker | Root, systemd and Docker on every machine |
| Nested virtualization | Not documented | Not documented | Yes, /dev/kvm for Android emulators and VMs |
| Shell access | Terminals, commands and files through the SDK; no SSH | execute_bash() API calls; each command runs in a new shell; no SSH | SSH, plus exec and files over the API |
| Pause and resume | Hibernates with a memory snapshot; resumes with processes still running | Pause keeps the file system and costs less; snapshots keep memory and files | Disk saved every minute and on stop; resume boots the machine again |
| Fork | Fork a hibernated sandbox from its snapshot, or a running one sharing its memory | Start many sandboxes from one memory snapshot (same image and architecture) | Fork a running sandbox with its disk |
| How long a sandbox lives | No hard cap; hibernates after an idle timeout of up to one day | TTL of up to 7 days for a custom container and 14 days for Code Execution, then deleted | No session cap on paid plans; you set the time to live |
| Reaching the sandbox | HTTPS host per port that wakes the VM on request; no raw TCP or public IP | Through Google's API or a private endpoint in your VPC; no public URL documented | HTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv6 or IPv4 |
| Outbound internet | Open; no egress allowlist | Off unless the template turns it on; routes through your VPC with Cloud NAT, a static IP or a firewall | Open internet on every plan; no provider-side allowlist |
| Desktop and browser | No desktop; a headless Chromium template | A browser in a container with a VNC live view, a click and type API, and CDP | Linux desktop streamed at 60fps, Chromium and computer-use tools |
| Coding agents | Run your own agent through the command API | Managed Agents API (Preview) runs Google's Antigravity harness | Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Secrets passed in as environment variables | You provision and scope the credentials the agent uses | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Hosting your agent code | You run your own agent loop inside a sandbox | Agent Runtime deploys ADK, LangGraph, LangChain, AG2 and LlamaIndex agents; idle time between turns is not billed | You run your own agent loop inside a sandbox |
| Regions | A country hint steers scheduling, for example to Europe; placement not guaranteed | 23 locations in the US, Europe, Asia, Canada, Australia and Brazil | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | CodeSandbox SDK | Google Agent Runtime | bochka |
|---|---|---|---|
| Full VM (own kernel) | Yes | No | Yes |
| Docker inside | Yes | No | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | No | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | No | Yes |
| Browser | No | Yes | Yes |
| Computer-use API | No | Yes | Yes |
| SSH | No | No | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | Yes | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | Yes | Yes |
| Memory fork | Yes | Yes | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | No | No |
| Wake on request | Yes | No | No |
| HTTPS preview URLs | Yes | No | Yes |
| Raw TCP inbound | No | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | Yes | No |
| Secret proxy | No | No | Yes |
| Secret proxy for any API | No | No | Yes |
| Preinstalled agents | No | Yes | Yes |
| Agent harness API | No | Yes | Yes |
| MCP server | No | No | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | No | Yes | No |
| Self-hosting | No | No | No |
| BYOC | No | No | No |
| Open source | No | No | No |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | No | Yes | Yes |
| Audit logs | Not published | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | No | Yes | No |
| EU data residency | No | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable CPU measurement for CodeSandbox SDK or Google Agent Runtime. bochka did 26.69 runs per second on the StarSling hpc-sandbox-benchmarks Node.js loop at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts, and neither of the other two was part of that run.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. CodeSandbox SDK and Google Agent Runtime 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 | CodeSandbox SDK, a month | Google Agent Runtime, 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 | $193 · Scale | $73 · Pay as you go | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $341 · Scale | $301 · 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 | $2,500 · Scale | $3,626 · 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 | $815 · Scale · with limits | $1,030 · 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 | $1,632 · Scale · with limits | $2,060 · Pay as you go | $2,000 · $2000/mo · with limits |
CodeSandbox SDK: You buy VM credits and each size burns a fixed number per hour, billed per started minute while the VM runs, including the idle time before it hibernates. The Scale plan adds a $170 monthly platform fee that is not usage credit, and a hibernated VM costs nothing.
Google Agent Runtime: Google bills $0.085 per vCPU-hour and $0.009 per GiB-hour allocated, rounded to the second, with the first 50 vCPU-hours and 100 GiB-hours free each month. Sandboxes are billed while they exist, a paused one costs less at an unpublished rate, and disk and egress rates are not published.
Google Agent Runtime: Plans start at $20 a month, and the whole fee is usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
CodeSandbox SDK's Scale plan allows 250 VMs at once, so the user-sandboxes and 1,000-job scenarios do not fit it, and each VM has a 20 GB disk with more disk and egress unpriced. Google fits those two but not the 50-agent fleet, because its sandboxes have no Docker inside, and it deletes a sandbox when its TTL ends and leaves disk and egress unpriced. bochka fits every scenario but the 1,000-job burst, where its start limits queue the jobs even on the $2,000 plan.
| Scenario | CodeSandbox SDK | Google Agent Runtime | bochka |
|---|---|---|---|
| One coding agent, workdays |
|
| None that bite |
| One agent that never stops |
|
| None that bite |
| 50 agents in parallel |
|
| None that bite |
| Sandboxes for your users |
|
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use CodeSandbox SDK when
your sandboxes need root and Docker, sleep between visits and should wake on the next HTTP request with their memory intact, and you are fine building on what Together now calls its legacy SDK.
- Root and Docker in every sandbox. Good for agents that install packages and build containers: each VM has root and Docker, which Google's sandboxes do not.
- Hibernation and wake on request. Useful for previews that sleep between visits: an HTTP request wakes a hibernated VM with its processes still running.
- Public HTTPS hosts per port. Good when people outside your team must open what the sandbox serves, with signed tokens if you want hosts private.
Use Google Agent Runtime when
you build agents with ADK or LangGraph on Google Cloud and want them hosted inside your own project, network rules and regions, with short code runs in a locked sandbox.
- A managed home for your agent code. Useful if you build agents with ADK or LangGraph: Agent Runtime hosts them and skips billing for idle time between turns.
- Inside your Google Cloud network. Useful if agents must stay in a Google Cloud perimeter, with egress off by default and routed through your own firewall.
- Regions worldwide and a ready browser. Useful if you need the US or Asia, or a browser with a live view for computer use: Google offers both.
Where bochka fits
If your agents do real work for hours, installing tools, running Docker and emulators, and serving apps other people open, both CodeSandbox SDK and Google leave gaps you fill yourself. bochka gives every agent a full VM with SSH, root, a desktop and coding agents built in, and keeps its disk with no session cap on paid plans.
A whole machine with /dev/kvm
Google's sandboxes run as appuser with no sudo or Docker, and CodeSandbox SDK has no SSH and no documented nested virtualization. On bochka, apt installs, docker compose and Android emulators all run, and you can SSH in.
Agents and keys built in
CodeSandbox SDK leaves the agent harness to you, and Google runs only its own Antigravity harness in Preview. bochka ships Claude Code and Codex driven from outside, and a credentials proxy keeps real keys out of the sandbox.
Sandboxes that stay and can be reached
A Google sandbox is deleted when its TTL ends and has no public URL. CodeSandbox SDK serves HTTPS only. bochka has no session cap on paid plans, HTTPS on up to 50 ports, raw TCP and a 60fps desktop.
Use bochka when your agents need a real computer for hours: root, Docker, SSH, /dev/kvm, a desktop and public URLs on a full VM that keeps its disk, with Claude Code, Codex and other coding agents built in. Compare it one to one: bochka vs CodeSandbox SDK and bochka vs Google Agent Runtime.
Questions people ask
Is CodeSandbox SDK cheaper than Google Agent Runtime?
It depends on the shape. One coding agent on workdays comes to $193 a month on CodeSandbox SDK and $73 on Google, and one agent running all month to $341 and $301. For 50 agents in parallel CodeSandbox SDK comes to $2,500 and Google to $3,626, though Google cannot run that fleet without Docker; bochka comes to $20, $26 and $317 for those three.
Which is faster?
Neither has a comparable CPU measurement in our data, so we cannot say. bochka did 26.69 runs per second on the StarSling Node.js benchmark at 4 vCPU / 8 GB.
Can CodeSandbox SDK or Google Agent Runtime run Docker?
CodeSandbox SDK runs Docker with root inside each Firecracker VM. Google's sandboxes run as the unprivileged user appuser with no sudo, and custom images must not need root, so Docker is not available. bochka runs Docker, systemd and /dev/kvm on every VM.
Is Google Agent Runtime the same as Vertex AI Agent Engine?
Yes. Google renamed Vertex AI Agent Engine to Agent Runtime in April 2026, as part of Gemini Enterprise Agent Platform. Its code, shell and browser sandboxes are a separate part of that platform called Agent Sandbox.
Is CodeSandbox SDK still maintained?
CodeSandbox is now part of Together AI. Together's docs call the CodeSandbox-based SDK deprecated and name together-sandbox as its successor, while self-serve sign-up still runs through CodeSandbox.
Can I SSH into either sandbox?
No. CodeSandbox SDK connects through its SDK with terminals, commands and files, and Google runs each command through an API call in a new shell. Every bochka sandbox has SSH as well as an exec and files API.
Try bochka
Install the CLI, then run bochka new.
Product preview
More comparisons
- bochka vs CodeSandbox SDK
- bochka vs Google Agent Runtime
- E2B vs CodeSandbox SDK
- Daytona vs CodeSandbox SDK
- Modal vs CodeSandbox SDK
- Vercel Sandbox vs CodeSandbox SDK
- Cloudflare Sandbox vs CodeSandbox SDK
- Blaxel vs CodeSandbox SDK
- Runloop vs CodeSandbox SDK
- Tensorlake vs CodeSandbox SDK
- Morph Cloud vs CodeSandbox SDK
- CodeSandbox SDK vs Northflank