AI Models Marketplace
for every developer
Rent premium GPUs, deploy LLM APIs, or earn from idle resources — all in one platform
300+ AI Models ready to use instantly
Access GPT, Claude, Gemini, Llama and hundreds of other AI models through a unified API
Everything in one platform
From GPU containers to LLM API marketplace — everything you need to build and deploy AI
AI Models Marketplace
OPENAI-COMPATIBLE · MULTI-PROVIDER
Access hundreds of AI models through a unified API. Streaming, failover, BYOK supported.
- OpenAI-compatible API
- GPT-4o, Claude, Gemini, Llama & 300+ models
- Pay-per-token or pay-per-request
- Streaming & Claude Code support
GPU Containers
DOCKER · NVIDIA GPU · PAY-PER-HOUR
Docker containers with premium NVIDIA GPUs. Shared and Dedicated GPU options.
- Shared GPU: GB VRAM × Price/GB/hour
- Dedicated GPU: entire device exclusively
- Built-in tunnel, no configuration needed
- Real-time GPU metrics & monitoring
Virtual Machines
LINUX · WINDOWS · SSH · RDP
Flexible Linux or Windows virtual machines with various configurations.
- Linux VMs (Ubuntu 22.04, 24.04)
- Windows VMs (Win10 Pro)
- Fast provisioning
- SSH (Linux) / RDP (Windows)
Clear pricing, no lock-in
Pay only for actual usage by the hour. Automatic billing every 5 minutes.
GPU Shared
Rent GPU by GB VRAM
- Share GPU with multiple containers
- Pricing: GB VRAM × Price/GB/hour × 20%
- Auto-pause when VRAM limit exceeded
- Real-time GPU metrics
- Free tunnel
GPU Dedicated
Rent entire GPU device
- Entire GPU device exclusively
- Pricing: GPU/hour × Number of GPUs
- Unlimited VRAM
- Full GPU utilization
- Free tunnel
Virtual Machine
Linux or Windows virtual machine
- Linux VMs (Ubuntu 22.04, Ubuntu 24.04)
- Windows VMs (Win10 Pro)
- Fast provisioning
- SSH access (Linux) / RDP access (Windows)
- Unlimited CPU & RAM
LLM API
Access AI models via API
- OpenAI-compatible API
- GPT-4o, Claude, Gemini, Llama
- Per-token or per-request billing
- Streaming & Claude Code support
- Multi-provider failover
Note: Prices may vary depending on the server and allocated resources.
First ports are exposed for free. Additional ports: 1 VND/min/port.
Everything you need
Built with powerful features to ensure the best performance, security, and user experience.
Powerful GPU
NVIDIA GPU support with Container Toolkit. Shared and Dedicated GPU options.
High Security
Docker namespaces, network isolation, strict resource limits. TLS encryption for WebSocket.
Real-time Monitoring
Monitor real-time metrics: CPU, RAM, GPU utilization, network bandwidth, storage usage.
Pay-per-use
Billed by actual usage hours. Automatic billing every 5 minutes. Only pay for what you use.
Fast Provisioning
Create containers or VMs in minutes. Automatic provisioning and tunnel setup.
Private Tunnel
Access containers/VMs via Tunnel without opening ports on the host. No NAT needed.
Multi-platform
Support both Linux and Windows VMs. SSH for Linux, RDP for Windows.
LLM API Marketplace
Access GPT-4o, Claude, Gemini via OpenAI-compatible API. Streaming, failover, Claude Code support.
How it works
Just 4 simple steps to get started. Fast, easy, no complex configuration needed.
Create an account
Sign up for free and top up your wallet. Supports Google, GitHub or username/password login.
Choose your resource
Select a container type (GPU/CPU) or VM (Linux/Windows). The system will show matching servers.
Launch and use
Container/VM will be created automatically in minutes. Get SSH/RDP credentials to access immediately.
Monitor and manage
View real-time metrics, manage containers/VMs, check billing history. Stop anytime.
Ready to get started?
Sign up now and get special offers for new customers. No credit card required.
View pricing