Free plan with 7-day free trial, 1 active deployment; Starter at $14.99/month for 5 active projects; Pay As You Go at $2.99 per deployment unit (one-time); Enterprise with custom technical solution design and flexible on-demand pricing.
CPU/RAM share: $3 per hour per whole CPU node; GPU/VRAM share: $6 per hour per full GPU card. Rates are set by individual hosts and metered by the second. App publisher fees apply to paid apps. Payments via USDC on Base network or card via Stripe.
Key features
Zero configuration deployment
Deploy to 50+ global regions
99.9% uptime with Kubernetes
ML model hosting with GPU acceleration
Seamless AI Studio integration
Container-native Docker deployment
Support for multiple frameworks
Auto-scaling infrastructure
Enterprise security with Zero Trust
WebAssembly portability across backends
Hardware attestation verification in browser
CPU isolation with Enclave Shield
GPU acceleration with masked offload
Per-second billing
AMD SEV-SNP confidential processor support
Encrypted volumes for apps
REST API and CLI control
On-chain deployment records
Decentralized host network
What makes it different
One-click deploy without DevOps knowledge required
Purpose-built for AI project deployment
Enterprise security with Zero Trust architecture
Combines convenience with enterprise-grade reliability
FlyPloy
Enclave