Cloud GPU rental with persistent workspace for AI work
Run AI models on your own hardware with automatic optimization and a single endpoint
Stage
Startup
Not given
Founded
2026
Not given
Based in
US
Not given
Pricing model
Paid
Open source
Pricing
Workspace: $0.24/hr. Machines: L4 (24 GB) from $1.40/hr, L40S (48 GB) from $2.64/hr, RTX PRO 6000 (96 GB) from $4.74/hr. System RAM options from 32 GB to 256 GB. Storage: $0.15 per GB-month written, shared folder $0.10 per GB-month, traffic out $0.10 per GB. New accounts get $10 credit to try after
Not given
Key features
Persistent workspace that pauses when idle, preserving files and apps
Snapshots to save and restore workspace setup
Shared folder accessible to all machines
One-click app installation including ComfyUI, PyTorch, Ollama, vLLM, JupyterLab, VS Code
Batch job support with automatic machine pause after completion
Multiple access methods: SSH, VS Code, native apps, AI assistants
Automatic pause after 15 minutes of inactivity, stopping GPU charges
Pay-by-minute billing with no monthly plan requirements
Claude MCP connector for AI assistant integration
Automatic model loading from Hugging Face and other sources
Hardware-aware model optimization for VRAM and context length
OpenAI-compatible endpoint
Support for multiple inference engines
Single unified endpoint for all models and machines
Distributed compute across multiple machines
Built-in app catalog with chat UIs and RAG tools
Integration with cloud providers
What makes it different
Unlike rented GPU pods that delete everything when stopped, Hinode keeps your workspace with all files, apps and models intact
Machines start with your apps and setup already installed via snapshots, no upload needed
Automatic pause after 15 minutes of inactivity eliminates wasted spend on idle GPUs
Shared folder lets all machines access models and datasets without copying
Pay by the minute from $10 prepaid credit with $10 trial for new users
Hinode
dotcore