Blaxel vs Ona
Blaxel is a sandbox API for agent products: Firecracker microVMs that sleep seconds after the last connection and wake in under 25 ms. Ona, formerly Gitpod and now part of OpenAI, is a cloud dev environment platform for engineering teams and its Codex agent, sold through sales.
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
Ona
Ona, formerly Gitpod, is a platform for cloud dev environments and background coding agents, and is now part of OpenAI.
Ona is a different kind of product from bochka: a dev-environment platform, not a sandbox API. Each task or developer gets an isolated VM built from a Dev Container config, which people open in a browser IDE, VS Code or JetBrains, and where Ona's Codex Agent can plan, code, test and open pull requests. It is built for engineering teams who want the same governed environment for every developer and agent; new customers run it in their own AWS or GCP account on an Enterprise contract.
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 | Ona: price rank | bochka: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Blaxel fits as a sandbox you start from code, while Ona's SDK to start environments from code is on the Enterprise plan only; bochka adds /dev/kvm and a real disk. | 10th cheapest of 367 $2,373 a month | 324th of 367, with limits $7,315 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Blaxel sleeps idle assistants and wakes them on request, while an always-on assistant on Ona needs auto-stop set to Never, because background work does not count as activity. | 12th cheapest of 366 $2,832 a month | 83rd of 366, with limits $8,504 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 is the strong pick here: short runs that sleep right away and resume in milliseconds are what it is built for, and Ona is not built for this at all. | 14th cheapest of 345 $144 a month | 335th of 345, with limits $5,320 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, Ona is built for your own engineers rather than your users, and bochka fits 300 users at once on a self-serve plan. | 101st of 361, with limits $926 a month | 330th of 361, with limits $5,988 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 | 77th of 360, with limits $4,378 a month | 283rd of 360, with limits $9,773 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 | 334th of 364, with limits $5,768 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 Blaxel starts fast sandboxes per job, Ona starts each run from a prebuild with no fork, and bochka can fork a warm machine. | 57th cheapest of 377 $431 a month | 365th of 377, with limits $5,461 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Ona is the better dev box of the two, with browser, VS Code and JetBrains IDEs and real SSH, while Blaxel has no native SSH; bochka is a full VM you leave on and reach over SSH. | 265th of 368, with limits $114 a month | 368th of 368, with limits $5,140 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 for computer use, Ona has no graphical desktop, and bochka streams a 60fps desktop you can embed. | 14th cheapest of 369 $634 a month | 353rd of 369, with limits $5,691 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 | 150th of 367, with limits $5,346 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 | 146th of 346, with limits $5,468 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 | 261st of 338, with limits $14,360 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 here with domain-level egress rules, Ona can only start new environments from a config, and bochka adds raw TCP and fork of a running machine. | 3rd cheapest of 360 $217 a month | 93rd of 360, with limits $5,228 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 | Ona | bochka |
|---|---|---|---|
| What it is | Sandbox API for agent products, plus batch jobs and MCP hosting | Cloud dev environment platform for engineers and the Codex Agent | Sandbox API for agents: full VMs you create, fork and stop from code |
| Isolation | Firecracker microVM per sandbox, own kernel | Isolated VM per environment, built from a Dev Container config | Full VM, own kernel, on dedicated AMD Ryzen 9 9950X hosts |
| Docker and nested virtualization | Docker with a Docker-in-sandbox image; no /dev/kvm | Docker and root in the Dev Container; nested virtualization not documented | Docker, root, systemd and /dev/kvm on every machine |
| Sleep and wake | Standby a few seconds after the last connection, wakes in under 25 ms with memory and processes | Stops after 30 idle minutes by default; background processes do not count; can be set to Never | Runs until you stop it; stop keeps the disk and costs nothing, resume boots the VM again |
| Files | Files live in memory (about half the RAM); one block volume can be attached at creation | Disk persists across stops; billed on your cloud while stopped; Core archives after 3 days | A real disk, snapshotted every minute and on stop, kept free while stopped |
| Fork | Fork with memory and running processes (private preview) | No environment copy | Fork a running sandbox into copies with its files |
| Starting point | Custom images built from Docker images | Dev Container config per repo, with scheduled prebuilds | Named snapshots (templates), shareable by code; no Dockerfile builds |
| Driving it from code | API and SDKs on self-serve tiers | Python, TypeScript and Go SDK on the Enterprise plan only | API and SDK on every plan, including the trial |
| Coding agents | Claude Code image you drive from its terminal or your own harness | Codex Agent from chat, a Linear issue or an automation; Claude Code you run yourself | Claude Code, Codex, OpenCode and more preinstalled, driven from outside with a prompt, steer and events API |
| SSH and IDEs | Terminal through bl connect; no native SSH | SSH, browser IDE, VS Code and JetBrains | Real SSH, root and systemd |
| Desktop and computer use | Desktop and browser for computer use | No graphical desktop inside the environment | 60fps desktop and Chromium, computer use and browser control, embeddable stream |
| Inbound traffic | Preview URL per port, public or token-protected; no raw TCP or public IP | HTTPS URL per port for you, your organization or everyone; no raw TCP documented | HTTPS URLs for up to 50 ports, token-protected; raw TCP; own IPv6 or IPv4 |
| Keys and outbound rules | Secret proxy for outbound HTTPS (public preview); domain, method and path rules; static egress IPs | Secrets injected as environment variables or files | AI credentials proxy for model providers and any HTTPS API; filter outbound with nftables in the VM |
| Where it runs | Oregon, North Virginia, London, Frankfurt | Enterprise runners in your own AWS or GCP account, many regions; GPU instance types available | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | Blaxel | Ona | bochka |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | No | Not published | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | Yes | No | Yes |
| SSH | No | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | No | Yes |
| Fork/clone | Yes | No | Yes |
| Live fork (no pause) | Yes | No | Yes |
| Memory fork | Yes | 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 | 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 | Yes | Yes |
| Agent harness API | No | Yes | Yes |
| MCP server | Yes | No | No |
| GPU | No | Yes | No |
| Windows | No | No | No |
| Arm64 | No | No | No |
| Self-hosting | No | No | No |
| BYOC | Yes | Yes | No |
| Open source | No | No | No |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | No | Yes | Yes |
| Usage per sandbox (API) | Yes | No | Yes |
| Audit logs | Not published | No | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Yes | No | No |
| EU data residency | Yes | Yes | Yes |
| Zero data retention | Yes | Not published | Yes |
Performance
On the same Node.js build-and-test benchmark at 4 vCPU and 8 GB, run on September 29, 2026, bochka did 26.69 runs per second and Blaxel 19.48, so bochka does about 1.4 times the work in the same time. There is no comparable measurement for Ona: it was not in the benchmark runs we use.
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). Ona 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 | Ona, 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 | $33 · Pay-as-you-go Tier 1 | $5,030 · Enterprise (AWS Marketplace 12-month contract) · 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 | $5,140 · Enterprise (AWS Marketplace 12-month contract) · 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 | $6,521 · Enterprise (AWS Marketplace 12-month contract) · 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 | $5,432 · Enterprise (AWS Marketplace 12-month contract) · 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 | $5,955 · Enterprise (AWS Marketplace 12-month contract) · 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 volumes are billed on their full size.
Ona: New Core subscriptions are closed, so the Ona prices here use its Enterprise listing on AWS Marketplace: a 12-month, $60,000 contract (about $5,000 a month), plus compute on your own AWS bill. Real Enterprise prices are negotiated with sales.
Ona: Your plan payment (from $20 a month) is all usage credit, billed per second while a machine runs. 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, and standby sandboxes count toward that, so 300 user sandboxes and 1,000 short jobs need a sales tier; the lower tiers also delete sandboxes after 7 or 30 days. No Ona scenario fits as published, because new customers can only buy Enterprise through sales, and the table assumes 3 environments at once since Ona publishes no Enterprise limit. On Ona, an idle agent stops after 30 minutes unless auto-stop is set to Never. bochka fits every scenario but the 1,000-job burst, where its starts-per-minute limit queues the jobs.
| Scenario | Blaxel | Ona | bochka |
|---|---|---|---|
| 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
your product starts many sandboxes from code that sit idle most of the time and must wake in milliseconds, or must run in the US.
- Sleeps in seconds, wakes in milliseconds. Useful if your sandboxes sit idle most of the time: one sleeps seconds after the last connection and wakes in under 25 ms.
- Self-serve sandbox API. Useful if your product starts sandboxes from code today: Blaxel's pay-as-you-go tiers need no sales call, unlike Ona.
- Network rules on the provider side. Blaxel can limit a sandbox to chosen domains, down to methods and paths, and give it static egress IPs.
Use Ona when
your engineers want a governed cloud IDE shared with a Codex agent, inside your own AWS or GCP account or with a GPU.
- A full cloud IDE for your team. Useful if your engineers work in the same environments as their agents: browser, VS Code and JetBrains IDEs with Dev Containers.
- Runs in your own cloud. Useful if environments must run inside your own AWS or GCP account: Ona's Enterprise runners do that.
- GPU environments. Useful if your agents need a GPU: Ona's Enterprise runners can use GPU instance types, such as one NVIDIA A10G.
Where bochka fits
If what you are really running is agents that do hours of work, look at bochka. Blaxel is built for sandboxes that sleep most of the time, and Ona is built for engineers in an IDE. bochka gives each agent a whole Linux machine with a real disk, a faster CPU than Blaxel, and agents you drive from outside, on a self-serve plan.
A whole Linux machine with /dev/kvm
Android emulators and microVMs need /dev/kvm. Blaxel's Firecracker guests do not get it and Ona does not document it, so that work does not start on either. bochka has it on every machine, with systemd and raw TCP.
A disk that keeps the work
Blaxel keeps files in memory, about half the RAM, unless you attach a volume at creation and pay for its full size. Ona bills a stopped disk on your cloud, and Core archives it after 3 days. bochka snapshots every minute and stops for free.
Agents driven from outside, on every plan
On Blaxel you build the agent harness yourself. On Ona the SDK needs an Enterprise contract, and the managed agent is Codex only. bochka ships Claude Code, Codex and others with one API to prompt, steer and read events.
Use bochka when your agents do real work for hours: builds, tests, Docker and emulators on a whole Linux machine with a real disk, a fast CPU, fork, and agents you drive from outside. Compare it one to one: bochka vs Blaxel and bochka vs Ona.
Questions people ask
Is Blaxel cheaper than Ona?
In every scenario we priced, yes, using Ona's Enterprise listing on AWS Marketplace since Core is closed: one agent running all month is $120 on Blaxel against $5,140 on Ona, and 50 agents in parallel $1,489 against $6,521. bochka comes to $26 and $317 for the same two. Ona's real price is a sales quote.
Which is faster, Blaxel or Ona?
Blaxel did 19.48 Node.js build-and-test runs per second at 4 vCPU and 8 GB, and bochka 26.69 in the same run. Ona was not in the benchmark, so there is no comparable number for it.
Can Blaxel and Ona run Docker?
Yes, both: Blaxel with its Docker-in-sandbox image, and Ona inside the Dev Container. Neither gives you /dev/kvm for Android emulators or VMs, while bochka does on every machine.
Is Ona the same as Gitpod?
Yes. Gitpod renamed itself Ona in 2025 and moved toward background coding agents, and Ona is now part of OpenAI. Blaxel, for its part, joined Baseten on September 10, 2026, with the product unchanged.
Can I sign up for Ona or Blaxel today?
Blaxel's pay-as-you-go tiers are self-serve. Ona's billing docs say new Core subscriptions are no longer available, so new customers go through sales for Enterprise. bochka's plans are self-serve, from a free trial up.
Can I SSH into Blaxel or Ona?
Ona gives you SSH plus browser, VS Code and JetBrains IDEs. Blaxel has no native SSH; you get a terminal through the bl connect command. bochka gives you real SSH with root and systemd.
Try bochka
Install the CLI, then run bochka new.
Product preview