Blaxel vs Together Code Sandbox
Blaxel is a self-serve sandbox cloud whose microVMs sleep seconds after the last connection and wake in under 25 ms with their memory. Together Code Sandbox starts VMs from Docker-image snapshots and can save their memory when they end, but Together has to turn it on for your organization.
The companies and products
Blaxel
Blaxel is a San Francisco company that runs cloud infrastructure for AI agents, and since September 2026 it is part of Baseten.
You get sandboxes, batch jobs, MCP server hosting and a model gateway. Each sandbox is a Firecracker microVM with its own kernel that drops to standby when nothing is connected and resumes in under 25 ms with its memory and running processes. It is built for agent products that start many sandboxes and want them asleep most of the time.
- Headquarters
- San Francisco, founded 2024
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 it must be enabled for your organization by Together. Together also sells Code Interpreter, a separate API that runs Python code in short sessions.
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. “10th cheapest of 367” means 9 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 | Blaxel: price rank | Together Code Sandbox: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Blaxel fits with Docker and an attached volume, Together's VMs need enabling and do not document Docker inside, and boat adds /dev/kvm and a real disk that stays. | 10th cheapest of 367 $2,373 a month | 65th of 367, with limits $528 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Blaxel lets a mostly idle assistant sleep and wake on request, Together has no idle detection or wake on request, and boat keeps the assistant on a full VM all month. | 12th cheapest of 366 $2,832 a month | 152nd of 366, with limits $1,095 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 Blaxel ranks 14th here, because short runs that sleep right away and wake in milliseconds are what it is built for, while Together's Code Interpreter bills a whole 60-minute session. | 14th cheapest of 345 $144 a month | 326th of 345, with limits $2,190 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 Blaxel's public tiers stop at 200 sandboxes at once, Together makes every port public with preview URLs still coming soon, and boat serves token-protected HTTPS to 300 users at once. | 101st of 361, with limits $926 a month | 234th of 361, with limits $900 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 Together can save a sandbox with its memory and start many copies from it, which suits branching rollouts, while Blaxel's fork with memory is in private preview. | 77th of 360, with limits $4,378 a month | 315th of 360, with limits $21,900 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 | 136th of 364, with limits $704 a month | 258th of 364, with limits $450 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 | 57th cheapest of 377 $431 a month | 251st of 377, with limits $180 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Neither Blaxel nor Together offers native SSH, while boat is a plain machine you SSH into and leave on. | 265th of 368, with limits $114 a month | 210th of 368, with limits $22 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 Blaxel runs a desktop and a browser, Together Code Sandbox has neither, and boat streams a 60fps desktop with Chromium. | 14th cheapest of 369 $634 a month | 184th of 369, with limits $600 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 | 16th cheapest of 367 $317 a month | 301st of 367, with limits $900 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 | 16th cheapest of 346 $215 a month | 219th of 346, with limits $180 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 | 147th of 338, with limits $4,292 a month | 124th of 338, with limits $3,600 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 Blaxel ranks 3rd with its domain-level egress rules, and boat gives root with raw TCP and nftables, while Together has no outbound rules documented. | 3rd cheapest of 360 $217 a month | 167th of 360, with limits $150 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 | Blaxel | Together Code Sandbox | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | A VM per sandbox on Together's infrastructure | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Getting started | Self-serve pay-as-you-go tiers; Tier 1 opens after $20 of top-ups, which become usage credit | The VM SDK and CLI must be enabled for your organization by Together; only Code Interpreter (Python) is self-serve | Sign up and start a sandbox from the API, CLI or dashboard |
| Machine size | Sized by RAM with CPU included (8 GB comes with 4 cores); up to 256 GB on Custom | 0.1 to 16 cores, 1 to 8 GB of memory per core; disk size fixed | 2 to 16 vCPU with 2 GB per vCPU, up to 16 vCPU / 32 GB on the $100 plan and above |
| Idle and wake | Standby a few seconds after the last connection; wakes in under 25 ms with memory and processes | Time to live counts from creation; no idle detection and no wake on request | Runs until you stop it or its time to live ends; a stopped sandbox costs nothing and resume boots it again |
| Disk | Files live in memory (about half the RAM); one block volume can be attached at creation | Disk size not configurable; kept by snapshotting the disk, or disk and memory, when a sandbox ends | A real disk that stays, snapshotted every minute and on stop |
| Fork | Fork with memory and running processes (private preview) | No live fork: the parent stops, then you start many sandboxes from its snapshot | Fork a running sandbox (disk); the original keeps running |
| Docker, root and SSH | Root and Docker with a Docker-in-sandbox image; terminal through bl connect, no native SSH | Commands run as user 1000 by default, root on request; Docker inside not documented; no SSH | Docker, systemd, root and real SSH on every machine |
| Nested virtualization | No: Firecracker guests do not get /dev/kvm | Not documented | Yes: /dev/kvm, so Android emulators and VMs run inside |
| Inbound traffic | Preview URL per port, public or token-protected; no raw TCP or public IP | All ports public; preview URLs coming soon; an experimental inbound allowlist by IP or token | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv6 or IPv4 |
| Outbound rules | Domain allow and deny lists, method and path rules, static egress IPs | No outbound allowlist documented | Open internet; filter inside the VM with nftables |
| Keeping API keys out of the sandbox | Proxy fills secrets into outbound HTTPS requests (public preview) | No credentials proxy documented | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Desktop and browser | Desktop and browser with computer-use control | None; headless command and file access only | Linux desktop streamed at 60fps, Chromium and computer-use tools |
| Coding agents | Claude Code image you drive from its terminal or your own harness | Run your own agent through execs; a Harbor guide for agent evals | Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API |
| Regions | US (Oregon, North Virginia), London, Frankfurt | Not published | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | Blaxel | Together Code Sandbox | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Not published | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | No | Not published | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | Yes | No | Yes |
| Computer-use API | Yes | No | Yes |
| SSH | No | No | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | No | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | No | 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 | Yes | Yes |
| Raw TCP inbound | No | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | No | No |
| Secret proxy | Yes | No | Yes |
| Secret proxy for any API | Yes | No | Yes |
| Preinstalled agents | Yes | No | Yes |
| Agent harness API | No | No | Yes |
| MCP server | Yes | Yes | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | No | No | No |
| Self-hosting | No | No | No |
| BYOC | Yes | No | No |
| Open source | No | No | No |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | No | Yes | Yes |
| Usage per sandbox (API) | Yes | Yes | Yes |
| Audit logs | Not published | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Yes | No | No |
| EU data residency | Yes | Not published | Yes |
| Zero data retention | Yes | Not published | Yes |
Performance
On the StarSling hpc-sandbox-benchmarks Node.js test at 4 vCPU / 8 GB, in the same run on September 29, 2026, boat did 26.69 runs per second and Blaxel 19.48, so boat got through about 1.4 times the work in the same time. Together Code Sandbox was not part of that run, so there is no comparable CPU measurement for it.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Blaxel measured on: Sandbox (active time, RAM-only pricing, CPU bundled). Together Code Sandbox has 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 | Blaxel, a month | Together Code Sandbox, 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 | $33 · Pay-as-you-go Tier 1 | $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 | $120 · Pay-as-you-go Tier 1 | $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 | $1,489 · Pay-as-you-go Tier 1 | $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 | $396 · Pay-as-you-go Tier 2 · with limits | $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 | $876 · Pay-as-you-go Tier 2 · with limits | $6,000 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | $2,000 · $2000/mo · with limits |
Blaxel: Blaxel charges for allocated RAM per second while a sandbox is active, with CPU included. In standby you pay only snapshot storage, and the tier you are on depends on how much you topped up in the last 30 days.
Together Code Sandbox: Together lists Code Sandbox at $0.0446 per vCPU-hour and $0.0149 per GiB-hour, but the VMs must be enabled for your organization, so the table prices Code Interpreter: $0.03 per 60-minute session from prepaid credits, $5 minimum. It runs only Python and keeps no disk, so it does not fit these scenarios.
Together Code Sandbox: Plans start at $20 a month, and the whole fee becomes usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
Blaxel's self-serve tiers allow 10, 50 or 200 sandboxes at once, counting those in standby, so the 300-user and 1,000-job scenarios need a sales tier, and Tier 0 and 1 delete sandboxes after 7 or 30 days. The Together column is Code Interpreter, and its limits decide every row: sessions last 60 minutes, nothing is kept after a session, it runs only Python and the machine size is not published. On boat the limit that bites is starts: 1,000 short jobs at once need more starts per hour and per day than even the $2,000 plan allows, so they are queued.
| Scenario | Blaxel | Together Code Sandbox | boat |
|---|---|---|---|
| One coding agent, workdays | None that bite |
| None that bite |
| One agent that never stops | None that bite |
| None that bite |
| 50 agents in parallel | None that bite |
| None that bite |
| Sandboxes for your users |
|
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Blaxel when
you want self-serve sandboxes that sleep most of the time and wake in milliseconds with their memory, with domain-level network rules or US regions.
- Sleeps in seconds, wakes in milliseconds. Good for sandboxes that sit idle most of the time: they sleep after the last connection and wake in under 25 ms.
- Self-serve today. Anyone can sign up and start microVMs on pay-as-you-go tiers, while Together's VM product needs Together to enable it first.
- Network rules and US regions. Blaxel can lock a sandbox to chosen domains with static egress IPs, and runs in Oregon, North Virginia, London and Frankfurt.
Use Together Code Sandbox when
you already run models on Together and want light VMs, from a tenth of a core, that you save with their memory and branch from, or a simple Python runner billed per session.
- Memory snapshots to branch from. Useful for rollouts and test variants: save a sandbox with its memory and start many copies with processes still running.
- Sandboxes next to your models. Handy if you already run inference or fine-tuning on Together: sandboxes and models share one account and API key.
- Very small machines and a Python runner. Sandboxes start at a tenth of a core, and the Code Interpreter API runs Python in sessions billed per 60 minutes.
Where boat fits
Blaxel is built for sandboxes that sleep most of the time, and Together Code Sandbox for light VMs you snapshot and branch, behind an access request. If your agents do real work for hours, with builds, Docker, emulators and servers other people reach, boat gives each one a whole Linux machine you can start today.
A whole Linux machine
Blaxel's Firecracker guests get no /dev/kvm and no native SSH, and Together runs commands as a normal user and documents neither Docker inside nor nested virtualization. Android emulators and VM tests do not start on either.
A disk that stays
Blaxel keeps files in memory, about half the RAM, unless you attach a volume at creation. Together keeps a disk only if you snapshot it when the sandbox ends. boat saves a real disk every minute and on stop.
Agents, desktop and keys built in
On Blaxel and Together you build the agent harness yourself, Together has no desktop or credentials proxy, and its ports are public. boat preinstalls coding agents with one API to drive them, a 60fps desktop and a credentials proxy.
Use boat when your agents do real work for hours: installs, builds, Docker, emulators, a browser and servers other people reach, on a full machine with a real disk, a faster CPU and the agent and its keys already set up. Compare it one to one: boat vs Blaxel and boat vs Together Code Sandbox.
Questions people ask
Is Blaxel cheaper than Together Code Sandbox?
The only self-serve Together price is Code Interpreter, which does not fit these scenarios, so a direct match is hard. For sandboxes for your users it is $396 on Blaxel against $900 on Together, and $200 on boat. For one coding agent on workdays Together's $5 is a Python runner that cannot keep files, against $33 on Blaxel and $20 on boat.
Which is faster, Blaxel or Together Code Sandbox?
Blaxel did 19.48 runs per second on the StarSling Node.js benchmark at 4 vCPU / 8 GB, and boat did 26.69 in the same run. Together Code Sandbox has no comparable measurement.
Can I run Docker on Blaxel or Together Code Sandbox?
On Blaxel, yes, with its Docker-in-sandbox image. Together builds sandboxes from Docker images, but its new SDK does not document Docker inside a sandbox and does not read Docker Compose. boat runs Docker, systemd and root on every machine.
Can I sign up for Together Code Sandbox like Blaxel?
Not for the VMs: the together-sandbox SDK and CLI must be enabled for your organization, and you ask Together for access. Code Interpreter is self-serve with prepaid credits. Blaxel and boat let you sign up and start sandboxes right away.
Do Blaxel and Together keep a sandbox's memory?
Both can. Blaxel saves memory and processes when a sandbox goes to standby and resumes them in under 25 ms. Together saves memory in a snapshot when a sandbox ends, and new sandboxes start from it with processes running. boat keeps the disk and reboots on resume.
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