ProvidersChecked 2026-10-28
Linux containers by default and real VMs on request, with a 15-minute idle stop, a 10 GiB disk cap and two regions.
Short answer: One always-on personal agent (2 vCPU / 4 GiB / 20 GiB) costs about $122.07 a month here, with a catch: 20 GiB of disk is over the 10 GiB limit. The AI model adds about $14.70 a month on top (GLM 5.3, 30 requests a day at 40k tokens each, median zero-retention price; from $6.84 at the cheapest host). Fits well: A Docker or Windows workload: the VM and Windows classes have their own kernel, and Docker-in-Docker is documented.
Daytona sells sandboxes for AI-generated code: a Linux container by default, or a Linux VM, Windows, GPU or macOS sandbox when the workload needs one. The unit is created and driven through five SDKs, a CLI, a REST API and an MCP server.
The classes are not interchangeable. Pause, resume, fork and memory snapshots exist only on the VM classes; archive exists only on containers; GPU sandboxes run in containers and vanish on stop.
It began as an open-source development-environment company. That repository is archived, and the managed platform is closed source.
| Who it is for | Teams building an agent product who want a fast container by default and a full VM when Docker, Windows or a real kernel is needed. |
|---|---|
| Isolation | Linux containers by default: dedicated namespaces, enforced resource limits and root inside, sharing the runner's kernel. Linux VM and Windows sandboxes have their own kernel. Docker-in-Docker is documented; nested virtualisation is Linux-VM only and must be enabled for the organisation. GPU sandboxes are containers with exclusive GPU allocation. |
| Sizes | Default 1 vCPU / 1 GB / 3 GiB; the organisation ceiling is 4 vCPU / 8 GB / 10 GiB of disk. Named presets include daytona-medium 2/4/8 and daytona-large 4/8/10; Windows presets go to 4/16/50. GPU sandboxes attach up to 8 GPUs, each adding up to 16 vCPU / 192 GB / 512 GB. Two shared regions, us and eu. |
| A personal agent here | About $122.07 a month for one always-on 2 vCPU / 4 GiB machine (2 vCPU / 4 GiB / 20 GiB), before the AI model. The catch: 20 GiB of disk is over the 10 GiB limit. Change the numbers |
| Recommended in |
|
Our reading of the sourced material on this page, not a provider claim.
Compare: alternatives to Daytona · E2B vs Daytona · Daytona vs Modal
| Model | Per-second billing on reserved resources, with no plan fee. Tiers are prepaid top-ups that set an organisation-wide pool. |
|---|---|
| Meter | vCPU $0.0504/hour, memory $0.0162/GiB-hour and disk $0.000108/GiB-hour after the first 5 GiB. Windows adds $0.0858/vCPU-hour, which reads either as a replacement rate or a surcharge. |
| While stopped | Stopped and paused sandboxes bill reserved disk only; memory is not billed. Archived and deleted sandboxes bill nothing. |
| Plan fee | No plan fee. Tier 1 needs only a verified email; Tier 2 is a $25 top-up, Tier 3 $500, and Tier 4 $2,000 every 30 days. |
| Minimum | $200 of free compute with no card, but it cannot be spent on GPU sandboxes. |
How Daytona lets you try before paying is on Trials and free tiers.
| Dashboard | Yes: a dashboard with a browser Playground for creating sandboxes and running SDK operations, plus Terminal and VNC tabs. |
|---|---|
| Without code | Partly. The Playground creates a sandbox and generates SDK snippets; operating one from the browser works, but building one is still a form of code. |
| Signup | Google or GitHub login, no card, $200 of free compute. Tier 1 needs only a verified email; GPU sandboxes cannot use the free credit. |
| Docs and support | Agent-readable docs with llms.txt and a 3.3 MB llms-full.txt, five SDKs, a CLI and a first-party MCP server. Support is email, Slack, chat, video and forums with no response-time commitment. |
Every capability the guide checks, with the catch where Daytona's version falls short. Compare all providers
From the profile's company section: the legal entity, who funds it, and what a buyer can check before signing.
Daytona Platforms Inc., at a New York address. Delaware incorporation is unconfirmed by the company; its terms name Delaware law.
“These Terms of Service ("Terms") are a binding contract between you ("you" or "Customer") and Daytona Platforms Inc.” daytona.io docs-confirmed
2023, by Ivan Burazin (CEO), Vedran Jukić (CTO) and Goran Draganić (Chief Architect).
“Daytona was founded in 2023 and evolved from our deep experience with developer workflows and infrastructure challenges.” daytona.io docs-confirmed
$91M total after a $60M Series B at a $1B valuation in October 2026, led by FirstMark Growth.
“a $60M Series B at a $1B valuation, led by FirstMark Growth, bringing our total funding to $91M” daytona.io docs-confirmed
Twelve people are named on the about page; no total is published.
not-published
Status page components showed 99.768% at the lowest. The SLA promises 99.95%, but credits go only to Tier 4 and above.
“Daytona will use commercially reasonable efforts to make the Services available 99.95% of the time in any given calendar month” daytona.io docs-confirmed
A SOC 2 Type II report covering December 2025 to March 2026 is available from the trust centre (checked 29 October 2026; earlier only a bridge letter was published). ISO 27001 is marked in progress while the badge is displayed.
“on July 28, 2026 with an unqualified opinion covering the period December 16, 2025” trust.daytona.io docs-confirmed
No notice period: fees may change by posting the change on the service.
“We reserve the right to modify fees and may do so by posting such modification on the Services or informing you through other reasonable methods.” daytona.io docs-confirmed
Shown as the research found them. A contradiction means the provider's own pages disagree; an open question means the answer is not published.
The sandboxes page claims a dedicated kernel for every sandbox and two paragraphs later says sandboxes run as Linux containers by default. The isolation page is explicit that containers get namespaces and only VM classes get their own kernel.
The homepage claims sub-90 ms from code to execution; the careers page says sub-200 ms. Neither is a measured figure for a cold sandbox.
The sandboxes page states a 10 GB per-sandbox disk maximum and, on the same page, lists Windows presets with 30 and 50 GB. Treating 10 GiB as the real Linux cap is the profile's judgement call: a 50 GiB Linux sandbox needs a raised limit with no published price or approval path beyond support.
The pricing page offers up to $50k in credits; the startups page offers up to $100k. Both are live.
The pricing page lists SSO and audit logs under Enterprise; the audit-log page gates them by role instead, and says compliance export is coming soon.
Any member of an organisation, and any API key valid for it, can exec in every running sandbox whatever their role. A write:sandboxes key can also mount any secret in the organisation.
It is not restricted to the port requested, opens the web terminal and the toolbox, and cannot be revoked. Signed URLs are the shareable form: 60 seconds by default, 24 hours maximum.
The public repo says development moved to a private codebase in June 2026. The managed service is closed source, so the archived code is not what you are buying.
The default docs are v0.226; /docs/en/v2/ documents an alpha with different API hosts and a different macOS model, including Daytona-managed Mac reservations.
List-price illustrations from the calculator, not quotes. Prices checked 29 October 2026.
A · 1,000 short tasks
$27.69
2 vCPU / 4 GiB / 10 GiB (plan: Pay as you go)
B · One always-on box
$245.32, with a catch
4 vCPU / 8 GiB / 50 GiB (plan: Pay as you go)
It cannot run this exactly as described: 50 GiB of disk is over the 10 GiB limit.
C · Three hours a day
$16.09, with a catch
2 vCPU / 4 GiB / 20 GiB (plan: Pay as you go)
It cannot run this exactly as described: 20 GiB of disk is over the 10 GiB limit.