Cheng Siong Chin This workflow corresponds to n8n.io template #9283 — we link there as the canonical source.
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": "vwBMikFazJ8dTN7C",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Compare AI Models with Nvidia API: Qwen, DeepSeek, Seed-OSS & Nemotron",
"tags": [],
"nodes": [
{
"id": "2fd77eab-0817-4d39-a206-4506b5373765",
"name": "Webhook Trigger",
"type": "n8n-nodes-base.webhook",
"position": [
-144,
-528
],
"parameters": {
"path": "6737b4b1-3c2f-47b9-89ff-a012c1fa4f29",
"options": {},
"httpMethod": "POST",
"responseMode": "responseNode"
},
"typeVersion": 2.1
},
{
"id": "1f78059c-f7a8-493c-886e-05047d83a7b4",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1072,
-848
],
"parameters": {
"width": 864,
"height": 944,
"content": "# Compare AI Models with Nvidia API: Qwen, DeepSeek, Seed-OSS & Nemotron\n\n## Overview\n- Queries four AI models simultaneously via Nvidia's API in 2-3 seconds\u20144x faster than sequential processing. Perfect for ensemble intelligence, model comparison, or redundancy.\n\n\n## How It Works\n- Webhook Trigger receives queries\n- AI Router distributes to four parallel branches: Qwen2, SyncGenInstruct, DeepSeek-v3.1, and Nvidia Nemotron\n- Merge Node aggregates responses (continues with partial results on timeout)\n- Format Response structures output\n- Webhook Response returns JSON with all model outputs\n\n## Prerequisites\n\n- Nvidia API key from [build.nvidia.com](https://build.nvidia.com) (free tier available)\n- n8n v1.0.0+ with HTTP access\n- Model access in Nvidia dashboard\n\n## Setup\n\n1. Import workflow JSON\n2. Configure HTTP nodes: Authentication \u2192 Header Auth \u2192 `Authorization: Bearer YOUR_TOKEN_HERE`\n3. Activate workflow and test\n\n## Customization\n\nAdjust temperature/max_tokens in HTTP nodes, add/remove models by duplicating nodes, change primary response selection in Format node, or add Redis caching for frequent queries.\n\n## Use Cases\n\nMulti-model chatbots, A/B testing, code review, research assistance, and production systems with AI fallback.\n"
},
"typeVersion": 1
},
{
"id": "e7f74b77-470b-49e4-a191-577afda45296",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-192,
-848
],
"parameters": {
"color": 3,
"width": 1312,
"height": 784,
"content": ""
},
"typeVersion": 1
},
{
"id": "8a0ca7d2-f4c0-4a95-9a7a-63c9d40ef77e",
"name": "Format Response",
"type": "n8n-nodes-base.set",
"position": [
720,
-544
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "bbfd9a05-0e6c-44cf-80e2-2a79ecb3f67a",
"name": "choices[0].message.content",
"type": "string",
"value": "={{ $json.choices[0].message.content }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "20e9c15e-cd3d-4624-8620-5e100081bab1",
"name": "Send Aggregated AI Model Responses",
"type": "n8n-nodes-base.respondToWebhook",
"position": [
944,
-544
],
"parameters": {
"options": {}
},
"typeVersion": 1.4
},
{
"id": "0b86c542-74ce-4456-b025-07025e6f57a7",
"name": "Merge AI Model",
"type": "n8n-nodes-base.merge",
"position": [
528,
-576
],
"parameters": {
"numberInputs": 4
},
"typeVersion": 3.2
},
{
"id": "556f837e-5958-4121-9142-f3a05b560190",
"name": "AI Model Router",
"type": "n8n-nodes-base.switch",
"position": [
80,
-576
],
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "8c79834b-efde-4096-8a97-687dbaac1eaa",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json['AI Model'] }}",
"rightValue": "1"
}
]
}
},
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "6f423cc4-08e3-41aa-8c5a-40a2d37a248d",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json['AI Model'] }}",
"rightValue": "2"
}
]
}
},
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "b8ba2c94-78d3-4325-8dda-e139d2dad24d",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json['AI Model'] }}",
"rightValue": "3"
}
]
}
},
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "0d1a15d3-047f-4489-896e-af2c079de4ae",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json['AI Model'] }}",
"rightValue": "4"
}
]
}
},
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "634191cd-73c9-4335-987b-93e07ba7ab0f",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json['AI Model'] }}",
"rightValue": "5"
}
]
}
}
]
},
"options": {}
},
"typeVersion": 3.2
},
{
"id": "38a42944-835b-422c-b872-b20c8f899210",
"name": "Query Qwen3-next-80b-a3b-thinking (Alibaba)",
"type": "n8n-nodes-base.httpRequest",
"position": [
304,
-832
],
"parameters": {
"url": "https://integrate.api.nvidia.com/v1/chat/completions",
"method": "POST",
"options": {},
"jsonBody": "={\n \"model\": \"qwen/qwen3-next-80b-a3b-thinking\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"{{ $('On form submission').item.json['Insert your Query'] }}\"\n }\n ],\n \"temperature\": 0.7,\n \"max_tokens\": 1024\n} ",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"headerParameters": {
"parameters": [
{
"name": "accept",
"value": "application/json"
}
]
}
},
"credentials": {
"httpBearerAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "0d948f27-f325-4776-88f5-17993c22f382",
"name": "Query Bytedance/seed-oss-36b-instruct (Bytedance)",
"type": "n8n-nodes-base.httpRequest",
"position": [
304,
-640
],
"parameters": {
"url": "https://integrate.api.nvidia.com/v1/chat/completions",
"method": "POST",
"options": {},
"jsonBody": "={\n \"model\": \"bytedance/seed-oss-36b-instruct\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"{{ $json['Insert your Query'] }}\"\n }\n ],\n \"temperature\": 1.1,\n \"top_p\": 0.95,\n \"max_tokens\": 4096,\n \"thinking_budget\": -1,\n \"frequency_penalty\": 0,\n \"presence_penalty\": 0,\n \"stream\": false\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType"
},
"credentials": {
"httpBearerAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "8fb1c1df-6544-4275-af67-c7f85b9fed92",
"name": "Query Nvidia-nemotron-nano-9b-v2 (Nvidia)",
"type": "n8n-nodes-base.httpRequest",
"position": [
304,
-256
],
"parameters": {
"url": "https://integrate.api.nvidia.com/v1/chat/completions",
"method": "POST",
"options": {},
"jsonBody": "{\n \"model\": \"nvidia/nvidia-nemotron-nano-9b-v2\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"/think\"\n }\n ],\n \"temperature\": 0.6,\n \"top_p\": 0.95,\n \"max_tokens\": 2048,\n \"min_thinking_tokens\": 1024,\n \"max_thinking_tokens\": 2048,\n \"frequency_penalty\": 0,\n \"presence_penalty\": 0,\n \"stream\": true\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"headerParameters": {
"parameters": [
{}
]
}
},
"credentials": {
"httpBearerAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "d0e9668b-1c75-4e41-90ec-684abeae0d49",
"name": "Query DeepSeekv3_1",
"type": "n8n-nodes-base.httpRequest",
"position": [
304,
-432
],
"parameters": {
"url": "https://integrate.api.nvidia.com/v1/chat/completions",
"method": "POST",
"options": {},
"jsonBody": "={\n \"model\": \"deepseek-ai/deepseek-r1\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"{{ $('On form submission').item.json['Insert your Query'] }}\"\n }\n ],\n \"temperature\": 0.6,\n \"top_p\": 0.7,\n \"frequency_penalty\": 0,\n \"presence_penalty\": 0,\n \"max_tokens\": 4096,\n \"stream\": true\n} ",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"headerParameters": {
"parameters": [
{
"name": "Accept",
"value": "application/json"
}
]
}
},
"credentials": {
"httpBearerAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "34faee65-7df2-4012-93bf-50660415c2d2",
"connections": {
"Merge AI Model": {
"main": [
[
{
"node": "Format Response",
"type": "main",
"index": 0
}
]
]
},
"AI Model Router": {
"main": [
[
{
"node": "Query Qwen3-next-80b-a3b-thinking (Alibaba)",
"type": "main",
"index": 0
}
],
[
{
"node": "Query Bytedance/seed-oss-36b-instruct (Bytedance)",
"type": "main",
"index": 0
}
],
[
{
"node": "Query DeepSeekv3_1",
"type": "main",
"index": 0
}
],
[
{
"node": "Query Nvidia-nemotron-nano-9b-v2 (Nvidia)",
"type": "main",
"index": 0
}
],
[
{
"node": "Query Qwen3-next-80b-a3b-thinking (Alibaba)",
"type": "main",
"index": 0
},
{
"node": "Query Bytedance/seed-oss-36b-instruct (Bytedance)",
"type": "main",
"index": 0
},
{
"node": "Query Nvidia-nemotron-nano-9b-v2 (Nvidia)",
"type": "main",
"index": 0
}
]
]
},
"Format Response": {
"main": [
[
{
"node": "Send Aggregated AI Model Responses",
"type": "main",
"index": 0
}
]
]
},
"Webhook Trigger": {
"main": [
[
{
"node": "AI Model Router",
"type": "main",
"index": 0
}
]
]
},
"Query DeepSeekv3_1": {
"main": [
[
{
"node": "Merge AI Model",
"type": "main",
"index": 2
}
]
]
},
"Query Nvidia-nemotron-nano-9b-v2 (Nvidia)": {
"main": [
[
{
"node": "Merge AI Model",
"type": "main",
"index": 3
}
]
]
},
"Query Qwen3-next-80b-a3b-thinking (Alibaba)": {
"main": [
[
{
"node": "Merge AI Model",
"type": "main",
"index": 0
}
]
]
},
"Query Bytedance/seed-oss-36b-instruct (Bytedance)": {
"main": [
[
{
"node": "Merge AI Model",
"type": "main",
"index": 1
}
]
]
}
}
}
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.
httpBearerAuth
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Queries four AI models simultaneously via Nvidia's API in 2-3 seconds—4x faster than sequential processing. Perfect for ensemble intelligence, model comparison, or redundancy. Webhook Trigger receives queries AI Router distributes to four parallel branches: Qwen2,…
Source: https://n8n.io/workflows/9283/ — 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 enterprise-level version control for your workflows using GitHub integration. Stop losing hours to broken workflows and manual exports – get proper commit history, visual di
n8n, Execute Workflow Trigger, HTTP Request +1
This flow creates dummy files for every item added in your *Arrs (Radarr/Sonarr) with the tag .
HTTP Request, Ssh
eek-Go v2 (Batch-Then-Review). Uses httpRequest. Webhook trigger; 75 nodes.
HTTP Request
This workflow receives webhook requests from a content calendar and uses the X API v2 to publish text posts, threads, image/video posts, and polls, as well as delete existing posts and run a credentia
HTTP Request
This workflow acts as a central API gateway for all technical indicator agents in the Binance Spot Market Quant AI system. It listens for incoming webhook requests and dynamically routes them to the c
HTTP Request