The execution layer your AI roadmap depends on, certified for production.
Platform teams need one runtime that every internal AI initiative can build on: isolated, compliant, observable and deployable where the data lives. Blaxel runs as managed cloud, with private networking into your VPC, or on your own metal.
Enterprise platform teams
SOC 2, HIPAA and ISO 27001 certified. Region support for data residency, hardware-level isolation, zero data retention and tier-based quotas up to 50,000+ concurrent sandboxes.
Up to $200 credits. No credit card required.
[CAPABILITIES]
Built for scale and security
-
Full observability
Logs, traces, and metrics for every agent run, out of the box.
-
Resume in ~25ms
Suspended agents come back with memory, processes and files intact.
-
Hardware isolation
One microVM per agent. No shared kernel, no cross-tenant reach.
-
Persistent memory
In-memory snapshots, volumes and Agent Drive keep state between runs.
-
Network control
Allow-lists, static IPs and secret injection on every workload.
-
Region support
Choose deployment regions for local data residency. Europe and US regions available.
-
Deploy anywhere
Managed cloud, private networking into your VPC, or bring-your-own-metal.
[SUSPEND WITHOUT LOSING A BYTE]
No base subscription. Fully usage-based.
In-memory storage is built for speed, and roughly half of a sandbox's memory is reserved for it. When a workload needs more room than memory allows, or data that must outlive the sandbox itself, attach a volume. Volumes trade some speed for durable, redundant capacity.
Explore Volumes[REPRESENTATIVE USAGE RATES]
Usage rates
Sandbox active CPU at $0.0000115 / GB RAM-second, snapshot storage at $0.20 / GB-month, images at $0.045 / GB-month.
Pay as-you-go
Usage-based pricing with infinite scalability.
$0.00USAGE
- Up to $200 in free credits
- Access to all Blaxel products
- Tier system for higher limits, up to 100,000+ sandboxes
- Full observability suite
- Community support on Discord
Start for free
Custom
For dedicated and custom deployments.
Custom pricing deployments. Contact us for a quote.
- All features of Pay-as-you-go, plus:
- Up to 256 GB RAM per sandbox or job
- Dedicated deployment locations
- Private network connectivity
- Connect servers from your own infra
Talk to us
[FAQ]
Frequently Asked Questions
- How fast does an agent resume after being idle?
- Sandboxes scale to zero after about 5 seconds of inactivity and resume from standby in roughly 25ms, even after weeks of being suspended.
- Does my agent keep its memory between runs?
- Yes. In-memory filesystem snapshots keep a suspended sandbox ready to resume. For guaranteed long-term persistence, attach a Volume or use Agent Drive, which can retain data for years.
- How isolated is each agent?
- Every agent runs in its own hardware-isolated microVM with full access to its filesystem, processes, and logs, plus native support for Zero Data Retention.
- How long can an agent run?
- Sandboxes are built for workloads lasting seconds to hours. For longer background work you can pair them with Batch API, which runs up to 24 hours.
- What does it cost to keep an agent on standby?
- You stop paying for compute while a sandbox is suspended. You only pay the standby snapshot storage rate to keep it ready for instant resume.