OpenRouter를 사용하는 자동화 AI 라우팅

• •AI 서비스 API Key(예: OpenAI, Anthropic 등)

{
  "id": "uNLWQ7BSozpoehpU",
  "meta": {
    "instanceId": "a4bfc93e975ca233ac45ed7c9227d84cf5a2329310525917adaf3312e10d5462",
    "templateCredsSetupCompleted": true
  },
  "name": "Automated AI Routing with OpenRouter",
  "tags": [],
  "nodes": [
    {
      "id": "25903a04-24d2-41f9-bf34-5d6234e642e5",
      "name": "채팅 메시지 수신 시",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        -180,
        -180
      ],
      "webhookId": "a0032740-26d8-491b-93f9-2250906d0e17",
      "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": {
          "id": "pb06rfB4xmxzVe3Q",
          "name": "OpenRouter"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "c53fe672-92cb-4d88-b4f6-f413fb00ad6a",
      "name": "Structured Output Parser",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        220,
        40
      ],
      "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": [
        380,
        40
      ],
      "parameters": {
        "model": "={{ $json.output.model }}",
        "options": {}
      },
      "credentials": {
        "openRouterApi": {
          "id": "pb06rfB4xmxzVe3Q",
          "name": "OpenRouter"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "ef9ceacb-55e4-4795-aa18-976997ec3717",
      "name": "스티키 노트",
      "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’s 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": "라우팅 에이전트",
      "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 에이전트",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        400,
        -180
      ],
      "parameters": {
        "text": "={{ $json.output.prompt }}",
        "options": {},
        "promptType": "define"
      },
      "typeVersion": 1.9
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "f1562281-3e44-4f7d-a585-90c54a65e888",
  "connections": {
    "4d688ad7-b463-4e72-9b79-4b9142f022d2": {
      "main": [
        [
          {
            "node": "94c49c22-9697-4230-ba35-5159041cfdc7",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "fabffdee-3c1e-47db-a4e9-f6473a6e9257": {
      "ai_languageModel": [
        [
          {
            "node": "4d688ad7-b463-4e72-9b79-4b9142f022d2",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "d60a9d61-c611-4813-bf85-e8f8faaa21b6": {
      "ai_languageModel": [
        [
          {
            "node": "94c49c22-9697-4230-ba35-5159041cfdc7",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "c53fe672-92cb-4d88-b4f6-f413fb00ad6a": {
      "ai_outputParser": [
        [
          {
            "node": "4d688ad7-b463-4e72-9b79-4b9142f022d2",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "25903a04-24d2-41f9-bf34-5d6234e642e5": {
      "main": [
        [
          {
            "node": "4d688ad7-b463-4e72-9b79-4b9142f022d2",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}