Rentals start at $5. Pricing varies by GPU model and availability. Hourly rates are shown at checkout with budget and estimated runtime calculated for the selected configuration.
Key features
Adapter registry with 191+ production-ready fine-tunes for discovery
In-browser A/B testing playground to compare adapters against base models
One-click deployment to serverless API endpoints with OpenAI-compatible format
Multi-adapter serving on single base model with zero cold starts
Automated fine-tuning with Unsloth-optimized kernels
Creator monetization with per-token revenue sharing
IP protection with managed endpoints and no public weight downloads
Framework integration as OpenAI-compatible proxy
Live GPU catalog with current inventory and pricing
Payment via x402 v2 or MPP without account signup
API, CLI, MCP server, and Agent Skill automation tools
SSH and Jupyter access to instances
Clean Ubuntu environment with NVIDIA CUDA preinstalled
Budget-based rental with transparent hourly pricing at checkout
Live ghost/stall fallback for failed provider instances
Money-back guarantee if GPU cannot be started
What makes it different
2x-5x faster fine-tuning using Unsloth-optimized kernels compared to traditional methods
Creators earn 70% revenue share on every token served through their adapters
No account required for agent payments via blockchain protocols
Flexible budget-based rental with live pricing
Multiple automation interfaces for developers
Telegram-based guided rental flow
Instant provisioning after payment with credentials delivered in minutes
AptAI
Ukiyo