Pay-as-you-go with no subscription. Models priced per 1M tokens in USD. For example, GPT-6 Luna: input $0.001, cache read $0.0001, output $0.005 per 1M tokens.
Key features
Launch machines in seconds
Auto-sleep when not in use
Wake up in milliseconds
Dedicated CPU, memory and disk per instance
Clone machines with same setup
Automatic routing without IP configuration
Standard tools support (docker, ssh)
Share routes with selective access
Unified API for multiple models with single base URL