Pay-per-token for language models, per-minute for audio, per-image for image generation, and per-hour for GPU rental. No long-term contracts or upfront costs.
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
100+ machine learning models
Developer-friendly APIs
Text generation models
Image generation with Flux
Automatic scaling
Custom model deployment
Zero data retention policy
SOC 2 and ISO 27001 certified
Dedicated GPU clusters
Multi-GPU setups with SXM connections
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
Own cutting-edge inference-optimized infrastructure with secure US-based data centers
Zero retention policy with SOC 2 and ISO 27001 certification for data privacy
No long-term contracts or hidden fees with simple pay-as-you-go pricing
100+ production-ready models covering all major AI use cases
Customizable inference solutions tailored to cost, latency, throughput or scale priorities
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