DeepSeek R1

Overview
DeepSeek R1 on OneCloudPlanet is an open reasoning model rivaling top commercial ones, deployed on your GPU instance. Complex logic, code and analysis — without sending data to external APIs.

What is DeepSeek R1?
DeepSeek R1 is a chain-of-thought reasoning model under the MIT license: unrestricted commercial use. Distilled versions (7B–70B) deliver strong reasoning on affordable GPUs.

Why DeepSeek R1 on OneCloudPlanet?
Privacy: prompts and answers never leave your instance.
Recommended configuration: 7–14B distills — 48 GB GPU (L40S); 32B–70B — A100 80 GB or multi-GPU. See Cloud GPU.
MIT license: no model fees — only the server.
OpenAI-compatible API: integrate without rewriting code.

How to launch
1) Sign in at console.ocplanet.cloud
2) Open Marketplace and choose DeepSeek R1
3) Pick a GPU configuration and location
4) Wait for deploy — the model is ready to serve
5) Connect via API or web UI

Post-deploy checklist
• Verify the model with a test API request
• Close ports with the free Firewall
• Add Dify from Marketplace for RAG and visual workflows
• Monitor GPU usage in the panel

FAQ
Which version to choose? 14–32B distills cover most tasks; full R1 requires a multi-GPU configuration.
Commercial use? Yes, MIT license — unrestricted.