Davide Boizza This workflow corresponds to n8n.io template #7004 — we link there as the canonical source.
This workflow follows the Agent → Chainllm 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": "abSdfsaYgkssXX7g",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Dynamically Selects Models Based on Input Type",
"tags": [],
"nodes": [
{
"id": "daf34daa-19e5-42a8-b820-5aa3d78c29a4",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-528,
-112
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "85be9290-50ac-457e-9fa1-0c00a88667da",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
160,
-112
],
"parameters": {
"text": "={{ $('When chat message received').item.json.chatInput }}",
"options": {
"returnIntermediateSteps": true
},
"promptType": "define"
},
"typeVersion": 2.1
},
{
"id": "0721d812-2dc6-4069-87e6-844b8f94214b",
"name": "Model Selector",
"type": "@n8n/n8n-nodes-langchain.modelSelector",
"position": [
80,
128
],
"parameters": {
"rules": {
"rule": [
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "976d83bb-7e9e-4aab-9722-25a9e238164f",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.output.request_type }}",
"rightValue": "coding"
}
]
}
},
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "1e68688d-73fe-47c1-9b35-a1e226220bcd",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.output.request_type }}",
"rightValue": "reasoning"
}
]
},
"modelIndex": 2
},
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "61d58197-db59-4cd7-bc41-bbeaf5e7b069",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.output.request_type }}",
"rightValue": "general"
}
]
},
"modelIndex": 3
},
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "fca2ec99-fd1d-458f-9919-73bfbba55c4f",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.output.request_type }}",
"rightValue": "search"
}
]
},
"modelIndex": 4
}
]
},
"numberInputs": 4
},
"typeVersion": 1
},
{
"id": "449b0bae-3749-493d-b6f6-dad155537bc9",
"name": "Structured Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
-80,
32
],
"parameters": {
"schemaType": "manual",
"inputSchema": "{\n\t\"type\": \"object\",\n\t\"properties\": {\n\t\t\"request_type\": {\n\t\t\t\"type\": \"string\"\n\t\t}\n\t}\n}"
},
"typeVersion": 1.3
},
{
"id": "03339701-3ed8-43c9-a490-3ebca30d39bb",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
400,
128
],
"parameters": {
"sessionKey": "={{ $('When chat message received').item.json.sessionId }}",
"sessionIdType": "customKey"
},
"typeVersion": 1.3
},
{
"id": "1d86d306-bbdd-45b0-9b96-fce0cbcdc0a0",
"name": "Request Type",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
-288,
-112
],
"parameters": {
"batching": {},
"messages": {
"messageValues": [
{
"message": "=Your task is to classify the type of request you receive as input.\nYou must provide the following output:\n- general: if it is a general request\n- reasoning: if it is a reasoning request\n- coding: if it is a request related to code development\n- search: if it is a request that involves the use of Google tools"
}
]
},
"hasOutputParser": true
},
"typeVersion": 1.7
},
{
"id": "f49883cd-fc48-4c26-8596-6267beb74c3d",
"name": "Opus 4",
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"position": [
-64,
352
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "claude-sonnet-4-20250514",
"cachedResultName": "Claude 4 Sonnet"
},
"options": {}
},
"credentials": {
"anthropicApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "0f19c20b-298b-45d8-b855-3a92c0dac675",
"name": "Gemini Thinking Pro",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
80,
352
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-thinking-exp"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "d2676326-64f2-47db-84f4-17fbf194d31b",
"name": "GPT 4.1 mini",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
224,
352
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "1f8d38d9-0298-4588-a763-7fac0132edf5",
"name": "Perplexity",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
352,
352
],
"parameters": {
"model": "perplexity/sonar",
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "fc7a67be-d46a-4fec-b1d2-9f8ce3b86462",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-320,
48
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "de2fc53a-bf97-475a-b978-0cde88483ee0",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-528,
-416
],
"parameters": {
"width": 624,
"height": 256,
"content": "## AI Orchestrator: dynamically Selects Models Based on Input Type\n\nThis 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 classification and model selection to optimize both performance and cost-efficiency in AI-driven conversations.\n\nIt dynamically routes requests to specialized AI models based on content type, optimizing response quality and efficiency."
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "d852ebdf-2860-4611-a58e-e58c8cd4cc35",
"connections": {
"Opus 4": {
"ai_languageModel": [
[
{
"node": "Model Selector",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Perplexity": {
"ai_languageModel": [
[
{
"node": "Model Selector",
"type": "ai_languageModel",
"index": 3
}
]
]
},
"GPT 4.1 mini": {
"ai_languageModel": [
[
{
"node": "Model Selector",
"type": "ai_languageModel",
"index": 2
}
]
]
},
"Request Type": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Model Selector": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Request Type",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Gemini Thinking Pro": {
"ai_languageModel": [
[
{
"node": "Model Selector",
"type": "ai_languageModel",
"index": 1
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "Request Type",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Request Type",
"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.
anthropicApigooglePalmApiopenAiApiopenRouterApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
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 classification and model selection to optimize both performance and cost-efficiency in…
Source: https://n8n.io/workflows/7004/ — 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 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
ModelRouter. Uses chatTrigger, agent, modelSelector, httpRequest. Chat trigger; 28 nodes.
Chat Trigger, Agent, Model Selector +8
This workflow creates an AI-powered chatbot that generates custom songs through an interactive conversation, then uploads the results to Google Drive.
Chat Trigger, Google Gemini Chat, Memory Buffer Window +7
This workflow implements a multi-model AI orchestration with the BEST models at now (ChatGPT 5.2, Claude Opus 4.6, Gemini 3 Pro) and response aggregation system designed to handle user chat inputs int
Chat Trigger, Chat, Google Gemini Chat +4
[](https://youtu.be/D11S0s3PDNc)
Chat Trigger, Memory Buffer Window, HTTP Request +7