Davide Boizza This workflow corresponds to n8n.io template #4237 — we link there as the canonical source.
This workflow follows the Agent → Chat Trigger recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"id": "uNLWQ7BSozpoehpU",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Automated AI Routing with OpenRouter",
"tags": [],
"nodes": [
{
"id": "25903a04-24d2-41f9-bf34-5d6234e642e5",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-180,
-180
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "fabffdee-3c1e-47db-a4e9-f6473a6e9257",
"name": "OpenRouter Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
0,
40
],
"parameters": {
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "c53fe672-92cb-4d88-b4f6-f413fb00ad6a",
"name": "Structured Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
340,
280
],
"parameters": {
"schemaType": "manual",
"inputSchema": "{\n\t\"type\": \"object\",\n\t\"properties\": {\n\t\t\"prompt\": {\n\t\t\t\"type\": \"string\"\n\t\t},\n\t\t\"model\": {\n\t\t\t\"type\": \"string\"\n\t\t}\n\t}\n}"
},
"typeVersion": 1.2
},
{
"id": "d60a9d61-c611-4813-bf85-e8f8faaa21b6",
"name": "OpenRouter Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
420,
40
],
"parameters": {
"model": "={{ $json.output.model }}",
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "ef9ceacb-55e4-4795-aa18-976997ec3717",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-180,
-420
],
"parameters": {
"width": 840,
"height": 180,
"content": "## Dynamic Model Selector for Optimal AI Responses\n\nThe **Agent Decisioner** is a dynamic, AI-powered routing system that automatically selects the most appropriate large language model (LLM) to respond to a user's query based on the query\u2019s content and purpose.\n\nThis workflow ensures **dynamic, optimized AI responses** by intelligently routing queries to the best-suited model."
},
"typeVersion": 1
},
{
"id": "4d688ad7-b463-4e72-9b79-4b9142f022d2",
"name": "Routing Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
40,
-180
],
"parameters": {
"options": {
"systemMessage": "=You are a **Routing Agent**.\n\nYour task is to analyze user queries and determine the most appropriate model to handle each specific use case.\n\n## Available Models\n\nYou have access to the following models:\n\n1. **perplexity/sonar**\n2. **openai/gpt-4o-mini**\n3. **anthropic/claude-3.7-sonnet**\n4. **meta-llama/llama-3-70b-instruct**\n5. **google/gemini-2.5-pro-preview**\n6. **qwen/qwen-qwq-32b**\n7. **openai/codex-mini**\n8. **openai/o1-pro**\n\n## Model Strengths\n\n### 1. perplexity/sonar\n- Built-in web search capability\n- Provides citations and customizable sources\n- Ideal for retrieving live, up-to-date information from the web\n\n### 2. openai/gpt-4o-mini\n- Cost-efficient language model optimized for advanced reasoning tasks\n- Excels in science and mathematics\n- Best suited for problems requiring careful, well-thought-out responses involving multiple variables or connections\n\n### 3. anthropic/claude-3.7-sonnet\n- High proficiency in coding tasks, scoring ~94% on SWE-Bench Verified\n- Enhances data science expertise by navigating unstructured data and utilizing multiple tools for insights\n- Handles very long documents and maintains coherence over extended conversations or analyses\n- Performs well in creative writing tasks such as storytelling, dialogue generation, and summarization\n- Tends to produce responses that are more aligned with safety and ethical guidelines\n\n### 4. meta-llama/llama-3-70b-instruct\n- Strong performance in coding and reasoning tasks\n- Suitable for complex programming and technical problem-solving\n- Supports long context windows, making it ideal for extended analyses\n\n### 5. google/gemini-2.5-pro-preview\n- Advanced multimodal capabilities, handling both text and images\n- Excels in tasks requiring integration of visual and textual information\n- Ideal for complex problem-solving involving diverse data types\n\n### 6. qwen/qwen-qwq-32b\n- Specialized in reasoning and problem-solving tasks\n- Effective in handling logical puzzles and complex analytical queries\n\n### 7. openai/codex-mini\n- Optimized for code generation and completion tasks\n- Suitable for lightweight coding tasks and quick code snippets\n\n### 8. openai/o1-pro\n- Designed for complex reasoning with enhanced computational resources\n- Performs well in STEM-related tasks, including physics, chemistry, and biology\n- Capable of handling large context windows, making it suitable for in-depth analyses\n\n## Output Format\n\nYour output must always be a valid JSON object in the following format:\n\n```json\n{\n \"prompt\": \"user query goes here\",\n \"model\": \"selected-model-name\"\n}\n```\n\n- The **\"prompt\"** field should contain the exact query to be sent to the selected model.\n- The **\"model\"** field should contain the model name (one of: perplexity/sonar, openai/gpt-4o-mini, anthropic/claude-3.7-sonnet, meta-llama/llama-3-70b-instruct, google/gemini-2.5-pro-preview, qwen/qwen-qwq-32b, openai/codex-mini, openai/o1-pro).\n\n**Important:** Only return the JSON object. Do not include any explanations or additional text."
},
"hasOutputParser": true
},
"typeVersion": 1.9
},
{
"id": "94c49c22-9697-4230-ba35-5159041cfdc7",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
400,
-180
],
"parameters": {
"text": "={{ $json.output.prompt }}",
"options": {},
"promptType": "define"
},
"typeVersion": 1.9
},
{
"id": "54c4278e-c185-4ab4-b21e-d8e837b14818",
"name": "Auto-fixing Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserAutofixing",
"position": [
140,
60
],
"parameters": {
"options": {
"prompt": "Instructions:\n--------------\n{instructions}\n--------------\nCompletion:\n--------------\n{completion}\n--------------\n\nAbove, the Completion did not satisfy the constraints given in the Instructions.\nError:\n--------------\n{error}\n--------------\n\nPlease try again. Please only respond with an answer that satisfies the constraints laid out in the Instructions:"
}
},
"typeVersion": 1
},
{
"id": "2813da6b-423b-41d6-8eb4-664f616ca8d5",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
140,
220
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "bb8e8d46-ce32-49e0-a843-496c6e026902",
"connections": {
"Routing Agent": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Auto-fixing Output Parser",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenRouter Chat Model": {
"ai_languageModel": [
[
{
"node": "Routing Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenRouter Chat Model1": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "Auto-fixing Output Parser",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Auto-fixing Output Parser": {
"ai_outputParser": [
[
{
"node": "Routing Agent",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Routing Agent",
"type": "main",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
openAiApiopenRouterApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
The Agent Decisioner is a dynamic, AI-powered routing system that automatically selects the most appropriate large language model (LLM) to respond to a user's query based on the query’s content and purpose.
Source: https://n8n.io/workflows/4237/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
This workflow is designed to intelligently route user queries to the most suitable large language model (LLM) based on the type of request received in a chat environment. It uses structured classifica
Chat Trigger, Agent, Model Selector +7
This n8n template provides a powerful AI-powered chatbot that acts as your personal Spotify DJ. Simply tell the chatbot what kind of music you're in the mood for, and it will intelligently create a cu
OpenAI Chat, Spotify, Chain Llm +7
This workflow researches prospects using MadKudu MCP, generates personalized emails with OpenAI, and syncs them to Outreach with automatic sequence enrollment. Its for SDRs and sales teams who want to
HTTP Request, Mcp Client Tool, Chat Trigger +4
ModelRouter. Uses chatTrigger, agent, modelSelector, httpRequest. Chat trigger; 28 nodes.
Chat Trigger, Agent, Model Selector +8
Turn any YouTube channel into a searchable knowledge base. The AI agent understands relationships between videos, topics, tools, and concepts - enabling powerful queries like "Which videos talk about
OpenRouter Chat, Agent, Chat Trigger +8