DeepSeek V3 Chat & R1 Reasoning Setup

Say goodbye to limited AI access in your automations!

This automation shows how to fully integrate DeepSeek’s powerful AI models — locally or via API — into any part of your n8n workflow, enabling advanced reasoning, memory-based chats, and flexible API calls with zero friction.

Perfect for developers, automation pros, and AI builders who want to explore DeepSeek's capabilities inside their own pipelines.

What it does:

🔌 Supports both local (Ollama) & cloud (DeepSeek API) integration
🧠 Uses DeepSeek Chat V3 for conversations, DeepSeek-R1 for reasoning
💬 Includes memory-enabled agent for context-aware replies
📡 Offers raw & JSON HTTP request options for full control
🚦 Built-in error handling and retry logic for stability

✅ Setup guide & importable automation included
🔧 Fully customizable: model type, memory config, message prompts, and deployment source

Need help setting it up? We offer full configuration and testing for a one-time fee