Starter plan is free with $30/month compute credits. Team plan is $250/month plus compute. Enterprise plan is custom. Compute is billed per second for CPU, GPU, and memory with no charges for idle time.
Standard: Free forever. Plus: €9/month. Pro: €25/month. Team plan: No subscription, pay per machine and per AI use from prepaid balance in US dollars. Machine sizes: R0 $5/month, R1 $10/month, R2 $30/month. AI pricing per million tokens: Rool® 1 input $0.35, cached input $0.07, output $0.70. Rool® 1
Key features
Serve LLMs, image, video, and audio models
Isolated environments for coding agents and RL rollouts
Fine-tune and train models on GPUs
Autoscale compute from zero to thousands of GPUs
Distributed storage for models and weights
Global capacity across 20+ clouds
Serverless functions with HTTPS endpoints
Out-of-the-box observability and logs
Persistent memory that builds knowledge graphs over time
File storage and management with version control
Collaboration with shared access and permissions
Multiple Rool Machines per account
Built-in connectors and custom MCP servers
Full data export and API access
Progressive Web App and mobile apps
Hourly credit refills with daily limits
Rool 1 and Rool 1.5 AI models
EU infrastructure with self-hosted models
What makes it different
Custom infrastructure built for AI including container runtime, storage, and scheduler
Sub-second container startup times for GPU workloads
Pay only by the second with no idle charges
Programmatically create millions of concurrent sandboxes
Private machine isolated at VM level, not just by access rules
Hosted entirely in the EU with self-hosted AI models