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.
Free trial: 14 days free. Starter: €40/month for 1 phone. Team: €129/month for 3 phones. Enterprise: custom pricing. Call minutes: €24/month for 100 minutes, €70/month for 300 minutes, €230/month for 1000 minutes. Android tablet: €69/month (on waiting list).
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
Real Android 13 OS with Samsung Galaxy S25 device profile
HTTP API for tap, type, swipe, launch, install, read, screenshot, mic
Google Play Store and alternative app installation
Accessibility tree and screenshot reading for screen understanding
Isolated containers with persistent app state between sessions
One-to-one voice calls with synthetic voice
APK upload and installation capability
MCP server support for local integration
Dashboard with device management and monitoring
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
Real Android device in the cloud, not a simulator or emulator
Agents interact via touchscreen like real users without app APIs
Persistent isolated containers per agent phone with no sharing
One-to-one voice calls enabling two-way agent communication
Flat monthly pricing with no runtime metering unlike competitors