Side by side
| E2B | Uno | |
|---|---|---|
| What it is | An API for agent sandboxes | A Linux computer with root and Docker, plus sites, storage and Uno AI |
| Isolation | Firecracker microVMs, with the stack open source under Apache-2.0, self-hostable | Firecracker microVM, one per computer, root inside |
| Monthly fee | Hobby: none, with a one-time $100 credit. Pro: $150, plus usage | Small $5, Plus $20, flat |
| Usage price | $0.0504 per vCPU-hour and $0.0162 per GiB-hour | None on top of the plan |
| 1 vCPU and 1 GB of memory, a month | $198.62 on Pro | $5 |
| 4 vCPU and 4 GB of memory, a month | $344.47 on Pro | $20 |
| Longest run before a pause | 1 hour on Hobby, 24 hours on Pro | there is no session time limit; it sleeps when idle and wakes with its memory |
| When idle | Pause keeps the filesystem and the memory, with running processes and loaded variables, indefinitely, until you kill the sandbox | Asleep after 10 minutes; memory and running programs are saved while it sleeps |
| Waking up | Resume takes about 1 second; a pause takes about 4 seconds for each GiB of memory | Median 118 ms through the console, from one measurement window |
| What wakes it | SDK calls and HTTP requests, once turned on: paused sandboxes can resume on SDK calls and on HTTP requests to their address, when autoResume is turned on (it is off by default) | you open it, a visitor opens your site, a message reaches your bot's webhook |
| Size | 1 to 8 vCPUs and 1 to 8 GiB of RAM, set per sandbox on Pro | From 1 vCPU and 1 GB to 32 vCPU and 48 GB |
| Disk | 10 GiB on Hobby and 20 GiB on Pro, included | 15 GB on Small, 40 GB on Plus; 25 GB of cloud storage on Small |
| Sandboxes at once | 20 on Hobby, 100 on Pro | One computer per agent; not built for hundreds of throwaway starts |
One machine switched on for a month, E2B Pro against Uno
Whole-month cost in $ per month. E2B is the Pro fee plus usage at the published rates; the machines are 1 vCPU and 1 GB of memory and 4 vCPU and 4 GB of memory.
Show as a table
| Option | $ per month | Shape |
|---|---|---|
| Uno Small, 1 vCPU · 1 GB | 5 | Flat price, sleeps when idle, keeps memory |
| E2B Pro, 1 vCPU · 1 GB | 199 | Pro fee plus 730 hours of usage |
| Uno Plus, 4 vCPU · 4 GB | 20 | Flat price, sleeps when idle, keeps memory |
| E2B Pro, 4 vCPU · 4 GB | 344 | Pro fee plus 730 hours of usage |
How we counted
730 hours in a month, one machine busy all of them: 730 × ($0.0504 + $0.0162) = $48.62 for 1 vCPU and 1 GB of memory. Add the $150 Pro fee: $198.62. Four times the usage plus the fee gives $344.47 for 4 vCPU and 4 GB of memory. Without the Pro fee, on Hobby, the usage alone is $49, but a Hobby run ends after 1 hour and the $100 credit is one-time. E2B does not say what a paused sandbox costs.
The same idea, a different shape
Both keep an agent's memory while it waits. E2B pauses a sandbox and resumes it in about 1 second; Uno puts a computer to sleep and wakes it on the first request. The memory is not what separates them. The price floor, the run cap and what comes with the machine are.
On E2B you pay for each hour the sandbox runs, so a short job is cheap and a machine kept busy for a month is not. On Uno the plan is flat: the agent can work all night and the price does not move. Past about 75 busy hours a month, flat wins.
Where Uno is worse
- Under about 75 busy hours a month, E2B usage billing is cheaper than $5: one hour of 1 vCPU and 1 GB of memory costs $0.0666, and Hobby has no monthly fee.
- Take E2B for sandbox fleets. It runs up to 100 sandboxes at once on Pro. An Uno computer is ready in about 2 seconds and is meant for one agent that stays.
- E2B: its stack is open source under Apache-2.0 and can be self-hosted. Uno is a hosted service only.
- Our vCPU are shared, not dedicated, and paid plans run in one region today: Netherlands.
- E2B quotes about 1 second to resume. Our median wake is 118 ms through the console, measured once in production. The two are not a side-by-side test.
Your agent gets a clean address of its own
Your computer runs in the Netherlands. Its traffic can leave through a static address of a regular internet provider in one of 8 countries. Only your account works from that address.
- From a data-center address
- Sites see a server range shared with thousands of strangers. The agent's browser hits more captchas and blocks.
- From your Clean exit IP
- Sites see a regular internet provider's address in the country you picked. Fewer captchas, and less reason for Claude or ChatGPT to flag your account: nobody else works from it.
One computer per agent, from $5 a month
Every plan is a Linux microVM with root and Docker. Pick the size; move up or down any time.
Small
A Telegram bot, a VPN, a small backend
$5/ month
- 1 vCPU · 1 GB
- 15 GB disk
- 25 GB cloud storage
- 5 boosts a month
Plus
Agents that work with your laptop closed
$20/ month
- 4 vCPU · 4 GB
- 40 GB disk
- 100 GB cloud storage
- Uno Work in the cloud
Pro
A product in production, a second MacBook
$70/ month
- 16 vCPU · 16 GB
- 120 GB disk
- 300 GB cloud storage
- Speed of a MacBook Air M4
Max
A team and many agents at once
$200/ month
- 32 vCPU · 48 GB
- 300 GB disk
- 1,024 GB cloud storage
- 5 public IPv4
Add Uno AI to any plan: 40 h of AI work a month on Small, 100 h on Plus, unlimited on Max. Today: GLM-5.3 Flash and MiMo v2.6 Pro. Or sign in with your own Claude or ChatGPT.