Overview
Claude, DeepSeek, GLM, Kimi and more behind one OpenAI-compatible endpoint
API reference
curl, Python and Node, ready to paste
Templates
Browse everything you can run
Deploy
Pick a card and a template, get a URL
GPU pricing
Billed by the minute, card by card
MCP server
Let Cursor, Claude Code or any AI agent rent a GPU or run jobs, with a budget you approve
Pick a template, click Deploy, get a browser URL.
Rent a raw GPU with JupyterLab + CUDA pre-installed. SSH access, root on a dedicated container, install any Python/CUDA libs you want. Billed per minute, stop anytime.
Loading templates...