Deploy private AI infrastructure in one click. Run Ollama, vLLM, Stable Diffusion, or any open-source model on dedicated hardware. Your data never leaves your server.
Virtualized CPU — Shared cores, great for most AI workloads. Best value for experimentation and moderate inference.
3B–7B models
8B–14B models
32B+ models
Click to deploy. No configuration needed. Each image is pre-optimized for the best performance on your plan.
Oobabooga's all-in-one interface. Load any model, any format.
Deploy text-generation-webuiGenerate images locally. ComfyUI + Automatic1111 pre-configured.
Deploy Stable DiffusionYour data never leaves your server. No API calls to third parties. Full privacy.
Run Llama 3, Mistral, Phi, Gemma, or any GGUF/HF model. Switch models anytime.
One-click install. Server + model runtime ready in under 60 seconds.
OpenAI-compatible endpoints. Use with any app, framework, or custom code.
SSH in, install anything, customize everything. It's your machine.
Run several models simultaneously on Pro and Enterprise plans.
Your server comes with a public IP. If you need a custom domain, configure these DNS records with your domain registrar.
Point your domain to the server IP
yourdomain.com → Server IPIPv6 address mapping (if available)
yourdomain.com → IPv6Alias for subdomains
api.yourdomain.com → yourdomain.comMaps IP back to your domain
Server IP → yourdomain.comDNS changes are managed through your domain registrar. Propagation typically takes 5–30 minutes.
No per-token fees. No rate limits. No data sharing. Run any model, any time, for a flat monthly price.