Cloud GPU rental with persistent workspace for AI work
Stage
Not given
Startup
Founded
Not given
2026
Based in
US
US
Pricing model
Paid
Paid
Pricing
DeepSeek V4.1 Flash with cached input from $0.008 per 1M tokens. DeepSeek V4.1 Flash Fast at up to 322 output tokens per second.
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
Key features
Prefix caching enabled by default
1 million token context window
Chat Completions and Responses
Streaming support
Tool calls
OpenAI-compatible API
Up to 322 output tokens per second
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
What makes it different
Lowest price per 1M tokens at $0.008 for cached input
Fastest inference speed at 322 output tokens per second
Built specifically for long-running agent workloads
Prefix caching on by default
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
CoralBricks
Hinode