Solution
Marketplace
OpenVPN (ISO)
Delivery Method: Kubernetes
Dify Premium
Deploy Dify Premium on OneCloudPlanet to build AI assistants faster with visual workflows, RAG pipelines, and API-ready delivery.
Ollama
Deploy Ollama with Open WebUI in one click: run Llama, Qwen, DeepSeek and other LLMs on your own GPU instance. Your data never leaves your server.
n8n
Install n8n in one click on a cloud instance: workflow automation and AI agents without n8n cloud plan limits. All data stays on your instance.
vLLM
Deploy vLLM in one click: a production LLM inference server with maximum throughput and an OpenAI-compatible API on your GPU.
ComfyUI
Deploy ComfyUI on a cloud GPU: SDXL/Flux image generation via visual workflows. No queues or subscriptions — your own generation server.
Qwen3-VL-32B-Instruct
Deploy Qwen3-VL-32B-Instruct in OneCloudPlanet for high-quality multimodal inference with long context, visual reasoning, and API-ready integration.
DeepSeek R1
Deploy DeepSeek R1 on your own GPU in one click: top-tier reasoning model with no data shared with third parties. Hourly billing.
Llama 3.1
Run Llama 3.1 (8B/70B) on your own GPU instance in one click: the most popular open LLM for chatbots, RAG and product AI features. Your data stays yours.
Whisper
Deploy Whisper on your own GPU: speech-to-text in 90+ languages. Transcription without sending recordings to third-party APIs.
Stable Diffusion WebUI
Deploy Stable Diffusion WebUI (Forge) on a cloud GPU in one click: SDXL/Flux image generation in the familiar UI, no limits or subscriptions.
PostgreSQL
Install PostgreSQL in one click on an NVMe cloud instance: a ready database for apps, analytics and AI (pgvector). Scheduled backups.