Supported libraries
Easy to use SDKs and CLI, coming soon.
How it works?
Tavor system architecture for programmatic code execution
System lifecycle
Execution flow
POST /api/v2/boxes
Key architecture traits
Built for production at scale
Built for the AI era
Secure your spot to shape the future of AI sandboxing
Run untrusted code safely
Leverage hardware-level isolation powered by Firecracker microVMs for unmatched security.
Optimized for AI workloads
Specifically built to safely and efficiently execute AI agent and LLM-generated code.
Performance on-demand
Effortlessly scale resources to match your application's exact requirements.
Flexible integrations & tools
Quickly integrate and deploy using SDKs across multiple languages and an intuitive command-line interface.
Keep sessions and state
Seamlessly support long-running tasks and stateful applications with optional persistent storage.
Granular network control
Easily manage and secure inbound and outbound connections with customizable network policies.
Pricing
Pay for actual compute. During our launch week, get twice the credits for each package you purchase!
Starter
Growth
Compute
vCPU
$0.000016/s
Custom pricing
Memory
GiB
$0.000002/s
Custom pricing
Plan limits
Max concurrent boxes
2
10+
Team seats
5
20+
Max CPU per box
2 vCPU
4+ vCPU
Max RAM per box
2 GB
8 GB
Starter
Compute (vCPU)
$0.000016/s
Memory (GiB)
$0.000002/s
Plan Limits
Max concurrent boxes
2
Team seats
5
Max CPU per box
2 vCPU
Max RAM per box
2 GB
Growth
Compute (vCPU)
Custom
Memory (GiB)
Custom
Plan Limits
Max concurrent boxes
10+
Team seats
20+
Max CPU per box
4+ vCPU
Max RAM per box
8 GB
* Each box currently includes 5 GB of storage for free. Additional storage and features may be available upon request.
Frequently asked questions
Can't find the answer you're looking for? Reach out to us at contact@tavor.dev.