# Smart query routing in chat: selects the best LLM based on task type
This workflow automates the processing of incoming chat messages by intelligently routing each query to the most suitable language model (LLM). It analyzes the query content using a LangChain agent and dynamically selects the optimal model — such as GPT, Claude, or Gemini — to generate accurate, context-aware responses. Ideal for AI-driven products where response quality and cost efficiency are critical.
## Who it´s for
- AI agent developers needing dynamic query distribution across models
- Companies using multiple LLMs and aiming to optimize response quality and cost
- Chat support teams leveraging different models for different query types
- AI researchers testing comparative model performance
- Product teams deploying adaptive AI solutions
## What the automation does
- Triggers on new chat messages
- Analyzes query content via a LangChain routing agent
- Routes tasks to the best-performing model (e.g., Perplexity for web search, Claude for coding, GPT for reasoning)
- Generates final response using the selected LLM
- Returns the generated answer back to the user in chat
## What´s included
- Ready-to-use n8n workflow
- Trigger and handler logic powered by LangChain and Structured Output Parser
- Integrations with OpenRouter, OpenAI, Anthropic, Google Gemini, Meta Llama, Qwen, and Perplexity
- Basic text instructions for setup and adaptation
## Requirements for setup
- n8n account
- OpenRouter account (or equivalent LLM aggregator)
- API keys for direct model access (if bypassing aggregator)
- Configured chat interface or test chat environment
## Benefits and outcomes
- Higher response accuracy through intelligent model selection
- Cost optimization by using lightweight models where appropriate
- Seamless handling of multimodal and specialized queries
- Simplified A/B testing and comparison of LLM performance
- Scalable, hands-free model switching without manual intervention
## Important: template only
Important: you are purchasing a ready-made automation workflow template only. Rollout into your infrastructure, connecting specific accounts and services, 1:1 setup help, custom adjustments for non-standard stacks and any consulting support are provided as a separate paid service at an individual rate. To discuss custom work or 1:1 help, contact via chat
No feedback yet