On this page · 2 min
Where boxd stands out
A real disk
Every boxd machine has a 100 GB disk that persists through sleep, stop and start. A Blaxel sandbox keeps its filesystem in RAM, about half of its memory, and needs a separate volume for anything durable.
Plain SSH
Every machine has its own SSH port. ssh my-machine.boxd works from any terminal, editor or agent, with no CLI tunnel and no token to refresh.
Claude Code, Codex and OpenCode are already there
Every machine boots with all three installed, plus headless Chrome, a desktop you can open in the browser, Docker and the boxd CLI. Your API keys stay outside the machine: the guest holds a placeholder and our proxy swaps in the real value.
A full Linux you control
Root, systemd, Docker and nested virtualization on the default image. On Blaxel, Docker needs a dedicated image and processes are managed through its sandbox API.
Timings are medians of ten runs on our production cluster, from a client in the same datacenter. How we measured
Side by side
Checked Oct 30, 2026. Each ↗ goes to where Blaxel says it. boxd's column is from our code and our own measurements.
| Feature | boxd | Blaxel |
|---|---|---|
| The machine | ||
| Full VM, own kernel | Yes, every machine | Yes, microVM↗ |
| Default size | 2 vCPU · 8 GiB · 100 GB | Not published↗ |
| Largest, self-serve | 8 vCPU · 32 GiB | Per tier, shown in console↗ |
| Root, systemd, Docker | Yes, plus nested virtualization | Root; Docker via a dedicated image↗ |
| CPU test (runs/s) | 12.6 (our run) | 18.03↗ |
| Composable | ||
| Ready machine described in code | Machine specs, built on one another | Images, branchable↗ |
| Machines create machines | Yes, signed in as the machine | SDK signs in on Blaxel↗ |
| Built-in integrations | 100+, credentials kept out | ~30, as MCP servers↗ |
| Schedules and event triggers | Cron and events; sleeps between runs | Schedules, job triggers↗ |
| Standalone disks | Yes, outlive the machine | Volumes, one sandbox at a time↗ |
| Private network between machines | Org network, split by tags | Not published↗ |
| Tailscale or NetBird | Both, built in | Tailscale image, your key↗ |
| Agent skills or MCP | Agent skills; no MCP server | Skills and MCP servers↗ |
| Ready when you are | ||
| Sleeps with processes kept | Yes, standby and hibernate | Yes, standby↗ |
| Wakes on a request | Yes, HTTPS or SSH · app answers in 156 ms | Implied, not documented↗ |
| Starts from a snapshot, app running | Yes · app answers in 1.19 s | Private preview (Carbon)↗ |
| Session limit | None | None stated |
| Built for agents | ||
| Coding agents installed | Claude Code, Codex, OpenCode | Opt-in Claude Code and Codex images↗ |
| SSH | Native, own port per machine | CLI terminal; SSH via Tailscale↗ |
| HTTPS URL per port | Yes, plus custom domains | Yes↗ |
| Raw TCP inbound | Yes, 3 ports per machine | Not documented↗ |
| Secrets kept out | Yes, swapped in at the proxy | Yes, proxy injection↗ |
| Price | ||
| vCPU-hour | $0.047, CPU used | Included in RAM price↗ |
| RAM GiB-hour | $0.014, memory in use | ≈$0.041 per GB-hour↗ |
| While asleep | Hibernated: disk only | Standby: snapshot storage↗ |
| Also worth knowing | ||
| GPUs | No | Not published↗ |
| Regions | Frankfurt (US waitlist) | Oregon, Virginia, London, Frankfurt↗ |
| SOC 2 | SOC 2 in progress | SOC 2 Type II↗ |
| SAML SSO | No | Yes↗ |
| Egress allowlist | Yes | Yes↗ |
| Self-host | Yes, free to 16 vCPUs | Your metal, their control plane↗ |
Where Blaxel is stronger
Resume speed. Blaxel suspends sandboxes seconds after they go idle and resumes them in about 25 ms by its own figures.
A kit of its own. Blaxel is as composable as boxd: about 30 integrations as MCP servers, schedules and job triggers, agent skills, and it hosts your agents and MCP servers next to the sandboxes.
CPU on this test. Blaxel scored 18.03 on the StarSling CPU test; boxd scored 12.6.
Regions. Oregon, Virginia, London and Frankfurt.
Compliance. SOC 2 Type II, ISO 27001 and HIPAA, plus SAML SSO.
Questions
- Where do my files live on Blaxel?
- In memory: by Blaxel's docs the sandbox filesystem takes about half of the sandbox's RAM, and durable data goes on a volume. A boxd machine has a 100 GB disk that survives sleep, stop and start.
- Which resumes faster?
- Blaxel quotes about 25 ms to resume. We measured the whole request instead: an HTTPS request to a hibernated boxd machine got the app's answer in 156 ms median, from inside the datacenter.