On-demand cloud macOS for AI agents, billed per minute
Stage
Not given
Startup
Founded
Not given
2026
Based in
Not given
Not given
Pricing model
Freemium
Paid
Pricing
Serverless inference with per-token pricing (pay for output, input, and cached tokens). Training pricing from $0.50 to $10.00 per 1M training tokens depending on model size and fine-tuning type. On-demand deployments at $0.134 to $0.334 per minute ($8 to $20 per hour) for various GPU types.
$0.90 per hour, billed per minute. Prepaid credit starts at $10, never expires and needs no subscription. Bigger top-ups add up to 20% bonus credit: $100 buys 133 hours. 7-day money-back guarantee on first purchase.
Key features
Guided training runs
Configuration-led training
Custom training logic
Serverless inference
On-demand dedicated deployments
Reserved capacity
OpenAI compatible API
Model library with latest open models
Reinforcement learning support
Multi-region deployments
Real macOS on Apple M6 or M5 Pro silicon, ready in about a minute
Full admin access with no password prompts
Xcode 27 preinstalled with Homebrew, Node, Python and CocoaPods
iOS Simulator with screenshots and screen recordings
Persistent 20 GB encrypted drive between sessions
Control via MCP, CLI, API or SSH
App Store submissions and TestFlight uploads
Secrets management without chat exposure
Desktop view and control in browser
What makes it different
Drop-in replacement for closed-model APIs with cost savings of 50-75%
Instant production deployment from any training checkpoint in seconds
Optimized inference engine for industry-leading throughput and latency
Elastic and global RL inference scaling
Own the complete learning loop for specialized intelligence
Agents work autonomously without human prompts or permission dialogs
Pay only for minutes used, not idle Mac time
Complete end-to-end app building and publishing from iOS Simulator to App Store
Built-in isolation and security with ephemeral sessions
NoMac