Upstash Box vs Instabox
Upstash Box gives each agent a light Docker container that pauses when idle and wakes on the next request, in three sizes, in the US. Instabox, which launched on 2026-10-14 as an invite-only beta, gives each agent a Firecracker virtual machine with Docker inside, in one size, free for now.
The companies and products
Upstash Box
Upstash Box is a cloud computer for AI agents from Upstash, the company known for serverless Redis, Vector and QStash.
Each box is a Docker container with its own filesystem, shell, git and an optional coding agent such as Claude Code, Codex or OpenCode, which you drive from TypeScript or Python SDKs. A box pauses when it sits idle, keeps its files, and you pay for the CPU it actually uses. Upstash built it to run its own Context7 service and opened it to everyone in March 2026.
Instabox
Instabox, made by InsForge, gives each AI agent its own Linux computer in the cloud. It launched on 2026-10-14 as an invite-only beta.
Each Instabox machine is a Firecracker microVM with its own kernel, root and Docker, started from one of four templates (agent-browser, universal, herdr or orca) or from your own snapshot. Every machine is 4 vCPU / 8 GiB with 20 GB of storage, and you drive it from a CLI, a TypeScript SDK or an HTTP API, with SSH, mosh, public port URLs and a desktop for computer use. It is aimed at developers who want a cloud box for a coding agent.
- Isolation
- Firecracker microVM per machine
- Machines per account
- 5, in any state: paused and stopped ones count
- Company
- InsForge AI, Inc.
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 345” means 9 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 | Upstash Box: price rank | Instabox: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory needs Docker for databases and test services: Instabox runs it inside its VMs, an Upstash box does not offer it, and boat runs it with systemd on machines up to 16 vCPU / 32 GB. | 61st of 367, with limits $464 a month | No published price | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Both can keep an agent going with no session cap: Upstash with a flat-price keep-alive box, Instabox by turning off its 30-minute idle pause. | 103rd of 366, with limits $475 a month | No published price | 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 Upstash suits short code runs: an idle box costs no CPU and a paused box wakes when work arrives, while Instabox caps an API exec call at 10 minutes, 4 at once. | 10th cheapest of 345 $119 a month | No published price | 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 Upstash runs 1,000 boxes at once and wakes a user's paused box on a request; Instabox allows 5 machines per account, so it cannot give each of many users a sandbox yet. | 2nd cheapest of 361 $222 a month | No published price | 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 | 352nd of 360, with limits $8,068 a month | No published price | 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 Instabox's 5-machine cap limits how many evals run at the same time, while Upstash and boat run many in parallel. | 52nd cheapest of 364 $1,011 a month | No published price | 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 or Android apps need Docker and /dev/kvm: Upstash offers neither, Instabox runs Docker but does not document /dev/kvm, and boat has both. | 120th cheapest of 377 $1,520 a month | No published price | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Both work as a cloud dev box: Upstash sells a flat-price keep-alive box, and Instabox adds mosh and paste-anywhere SSH tokens on its free beta. | 10th cheapest of 368 $20 a month | No published price | 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 Computer-use agents need a screen: Upstash's browser is headless with no desktop, Instabox has a Linux desktop on one template, and boat streams one at 60fps. | 73rd of 369, with limits $76 a month | No published price | 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 | 49th of 367, with limits $38 a month | No published price | 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 | 37th cheapest of 346 $400 a month | No published price | 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 | 200th of 338, with limits $8,000 a month | No published price | 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 | 225th of 360, with limits $259 a month | No published price | 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 | No published price | 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 | No published price | Can't run it |
Key features
| Feature | Upstash Box | Instabox | boat |
|---|---|---|---|
| Isolation | Docker container per box on AWS | Firecracker microVM with its own kernel and root | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Docker inside | Not documented; the box is itself a Docker container, and custom images are listed as coming soon | Docker and Docker Compose run inside | Docker and Compose run inside, with root and systemd |
| Nested virtualization | No; boxes are containers with no VM support documented | Not documented | Yes, /dev/kvm for Android emulators and VMs |
| Machine sizes and disk | Small 2 vCPU / 4 GB, Medium 4 vCPU / 8 GB, Large 8 vCPU / 16 GB, with 5, 10 or 20 GB disk | One size for everyone: 4 vCPU / 8 GiB with 20 GB storage; other sizes are refused | Several sizes up to 16 vCPU / 32 GB on the $100 plan and above; 50 GB disk at 4 vCPU / 8 GB |
| Machines at once | 10 on Free, 1,000 on Pay as You Go, raised on request | 5 per account, in any state: paused and stopped ones count | No session cap on paid plans; start rate is limited by plan |
| Idle and pause | Pauses itself when idle and keeps its files; an idle box costs no CPU | Pause keeps memory and running programs; resume usually takes about a second | Disk saved every minute and on stop; a stopped sandbox costs nothing |
| Wake on request | Yes; a request to a public URL resumes a paused box | No; port URLs go offline while the machine is paused, and a visit does not wake it | No; a stopped sandbox is started by API |
| Fork | Snapshot a running box and start many new boxes from it | Fork copies a stopped machine only; saving a snapshot stops a running machine first unless the server allows a live save | Fork a running sandbox with its disk |
| Public port URLs | HTTPS URL per port, public unless you add a token or basic auth; no raw TCP | HTTPS on up to 16 ports, open to anyone with the URL | HTTPS on up to 50 ports, token-protected by default; raw TCP too |
| SSH | SSH through a gateway | SSH through a gateway with short-lived certificates, paste-anywhere SSH tokens and mosh | SSH into every sandbox |
| Desktop and browser | Managed headless Chromium with AI page actions and CDP; no desktop | Linux desktop with a browser on one template, screenshot and click API, shareable view or control links | Linux desktop streamed at 60fps, Chromium and computer-use tools |
| Coding agents | Claude Code, Codex and OpenCode built in, with run and stream APIs, webhooks and scheduled prompts | Templates and saved agent sign-ins in snapshots; you run the agent yourself | Seven agents preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Host proxy injects headers into outbound HTTPS on port 443; set when the box is created | Vault writes your secrets into each machine as environment variables or files | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Regions | US only (AWS us-east-1) | Not published | EU only (Germany, Finland, France) |
Every feature Battleships tracks (43)
| Feature | Upstash Box | Instabox | boat |
|---|---|---|---|
| Full VM (own kernel) | No | Yes | Yes |
| Docker inside | No | Yes | Yes |
| Nested virtualization | No | Not published | Yes |
| Root | Not published | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | Yes | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | No | Yes | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | No | No | Yes |
| Fork/clone | Yes | Yes | 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 | No | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Not published | No |
| Secret proxy | Yes | No | Yes |
| Secret proxy for any API | Yes | No | Yes |
| Preinstalled agents | Yes | Not published | Yes |
| Agent harness API | Yes | Not published | Yes |
| MCP server | Yes | Not published | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | Yes | Not published | No |
| Self-hosting | No | Not published | No |
| BYOC | No | Not published | No |
| Open source | No | No | No |
| Scoped API keys | Not published | Yes | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | Yes | Yes | Yes |
| Audit logs | Not published | Not published | No |
| SSO | No | No | No |
| SOC 2 | Yes | Not published | No |
| HIPAA | No | Not published | No |
| EU data residency | No | Not published | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
Neither Upstash Box nor Instabox has a result in the hpc-sandbox-benchmarks CPU test, so there is no comparable measurement between them and this page makes no speed claim either way. boat did 26.69 runs per second on that Node.js build-and-test loop at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts. Instabox says a new machine's shell is ready in under a second; that has not been measured.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Upstash Box and Instabox 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 | Upstash Box, a month | Instabox, 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 | $21 · Pay as You Go | No published price | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $21 · Pay as You Go | No published price | $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 | $900 · Pay as You Go · with limits | No published price | $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 | $306 · Pay as You Go | No published price | $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 | $1,822 · Pay as You Go | No published price | $2,000 · $2000/mo · with limits |
Upstash Box: A standard box is billed for the CPU it actually uses, at $0.10, $0.20 or $0.40 per active CPU hour for Small, Medium and Large, plus $0.10 per GB-month of storage, and RAM is free. A keep-alive box costs a flat $8, $16 or $32 a month whether it is busy or not.
Instabox: Instabox is free during the beta ("Free until we figure it out", 5 machines per user) and has no published price, so no bill can be compared yet.
Instabox: Plans start at $20 a month, and the whole fee is usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
Upstash does not offer Docker inside a box, so the 50-agent scenario does not fit there, and its disks stop at 5, 10 or 20 GB by size, with egress price not published. Instabox allows 5 machines per account, paused and stopped ones included, so the 50-agent and user-sandbox scenarios do not fit it, and with no published rate none of the scenarios can be priced. Every Instabox machine is 4 vCPU / 8 GiB with 20 GB storage, and an API exec call runs at most 10 minutes, with 4 at once. boat's limit is start rate: for 1,000 short jobs at once, even the $2,000 plan queues the burst.
| Scenario | Upstash Box | Instabox | boat |
|---|---|---|---|
| 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 Upstash Box when
your agents mostly wait, need to wake on an incoming request, must stay inside an outbound allowlist, or need many boxes at once in the US.
- Idle costs no CPU, and a request wakes the box. Good for agents that wait a lot: an idle box costs no CPU, and a request to its URL wakes it.
- Many boxes, several sizes. Runs 1,000 boxes at once on Pay as You Go in three sizes, where Instabox allows 5 machines of one size.
- Outbound network rules. Useful when an agent may only reach a short list of domains or IP ranges, changeable on a running box.
Use Instabox when
you have a beta invite and want to try a few free 4 vCPU / 8 GiB VMs with Docker, memory pause and mosh.
- A VM with Docker inside. Each machine is a Firecracker VM with its own kernel and root, so Docker and Compose run inside it.
- Pause with memory. A paused machine keeps its memory and running programs and usually resumes in about a second.
- Free during the beta. For trying things out: during the invite-only beta, each account runs 5 machines of 4 vCPU / 8 GiB for free.
Where boat fits
Look at boat when your agents need a whole Linux machine that you can plan around: Docker with systemd and /dev/kvm, bigger sizes, private port URLs and published terms. Upstash Box is a light container, and Instabox is a one-size beta with 5 machines per account.
Docker, systemd and /dev/kvm in one machine
An Upstash box is itself a container, so an agent that starts a database in Docker gets stuck. Instabox runs Docker but does not document /dev/kvm, so Android emulators are out. boat has all three.
Branch work without stopping it
Instabox forks only a stopped machine, so branching mid-task ends the agent's running programs. Upstash snapshots a running box, but its disk stops at 20 GB. boat forks a running sandbox and saves its disk every minute.
Port URLs that stay private
Agents serve half-built apps and admin panels. Instabox URLs are open to anyone, and Upstash URLs are public until you add a token or basic auth. boat URLs carry a token by default, on 50 ports plus raw TCP.
Use boat when your agents need a real machine with Docker, /dev/kvm and a desktop, fork running work, serve private URLs or need bigger sizes, on terms published today. Compare it one to one: boat vs Upstash Box and boat vs Instabox.
Questions people ask
Is Upstash Box cheaper than Instabox?
It can't be compared yet. Instabox is free during its beta and publishes no price, so there is no bill to set against Upstash's. Upstash bills per active CPU hour, and for one coding agent on workdays it comes to $21 a month.
Which is faster, Upstash Box or Instabox?
Neither has been measured in the hpc-sandbox-benchmarks CPU test, so there is no fair answer. Instabox says a new machine's shell is ready in under a second, and its docs say a paused machine usually resumes in about a second; neither has been measured here.
Can Upstash Box or Instabox run Docker?
Instabox can: each machine is a Firecracker VM, and Docker and Docker Compose run inside. Upstash's docs do not offer it, since each box is itself a Docker container. boat runs Docker, Compose and systemd in every sandbox.
Which one has a desktop for computer use?
Instabox has a Linux desktop with a browser on one template, with a screenshot and click API, and you bring the model. Upstash gives a headless Chromium with no desktop. boat streams a full Linux desktop at 60fps with computer-use tools preinstalled.
Can I sign up for Instabox today?
It launched on 2026-10-14 as an invite-only beta, with sign-in through GitHub or Google. Upstash Box has been open to everyone since March 2026, with a Free plan and Pay as You Go.
Where do Upstash Box and Instabox run?
Upstash Box runs in AWS us-east-1 in the US, with more regions planned. Instabox does not publish its regions. boat runs in the EU, in Germany, Finland and France.
Try boat
Install the CLI, then run boat new.
7-day free trial