This workflow corresponds to n8n.io template #6746 — we link there as the canonical source.
This workflow follows the Chat Trigger → HTTP Request 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": "k4dOhz5YNYLVPUs1",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "dolphin",
"tags": [],
"nodes": [
{
"id": "15298662-69ee-4458-a792-9f4878b5fcbd",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-272,
0
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "db22e3ea-e88c-463f-bfc8-5897765e10c9",
"name": "Generate Chat Completion",
"type": "n8n-nodes-base.httpRequest",
"position": [
176,
0
],
"parameters": {
"url": "https://api.novita.ai/v3/openai/chat/completions",
"method": "POST",
"options": {},
"jsonBody": "={\n \"model\": \"cognitivecomputations/dolphin-mixtral-8x22b\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"{{ $json.systemPrompt }}\"\n },\n {\n \"role\": \"user\",\n \"content\": \"{{ $('When chat message received').item.json.chatInput }}\"\n }\n ],\n \"max_tokens\": {{ $json.MaxTokens }}\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "=Bearer {{ $json.NovitaKey }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "301be5e4-8b78-44c6-83d2-c5a62f6074ef",
"name": "Return output",
"type": "n8n-nodes-base.set",
"position": [
400,
0
],
"parameters": {
"options": {
"ignoreConversionErrors": false
},
"assignments": {
"assignments": [
{
"id": "a497c430-1449-48dd-915b-6c922ec0d56d",
"name": "output",
"type": "string",
"value": "={{ $json.choices[0].message.content.trim() }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "0fead77e-12d8-40d5-a305-0dec2ea6663a",
"name": "Set fields",
"type": "n8n-nodes-base.set",
"position": [
-64,
0
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "fef0c4b6-9451-4848-b681-7ed11461637e",
"name": "NovitaKey",
"type": "string",
"value": "yourNovitakey"
},
{
"id": "215393bd-94bf-4de1-8915-89ccb38f531e",
"name": "MaxTokens",
"type": "number",
"value": 500
},
{
"id": "f987e35d-b291-47b6-b9de-1e5a0d16d468",
"name": "systemPrompt",
"type": "string",
"value": "you are a professional AI helper."
}
]
}
},
"typeVersion": 3.4
},
{
"id": "3fb3452f-0d2a-4da8-9306-f2ca6de2cf0c",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-288,
208
],
"parameters": {
"width": 800,
"height": 240,
"content": "## Requirements \n- Create a [Novita](https://novita.ai/?ref=mze5m2e&utm_source=affiliate) account\n- Get your Novita api key\n\n## How it works\n- Set your fields and add more parameters as needed into the endpoint\n- Review the [novita docs](https://novita.ai/docs/api-reference/model-apis-llm-create-chat-completion) for chat completions"
},
"typeVersion": 1
},
{
"id": "f0781099-1e79-47e0-997e-fa34593406df",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-128,
-128
],
"parameters": {
"color": 4,
"width": 224,
"height": 320,
"content": "## Config \nSet fields to pass into the chat completion api"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "9bd09b4b-66e4-472c-b7ff-410e7ff59f2f",
"connections": {
"Set fields": {
"main": [
[
{
"node": "Generate Chat Completion",
"type": "main",
"index": 0
}
]
]
},
"Generate Chat Completion": {
"main": [
[
{
"node": "Return output",
"type": "main",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Set fields",
"type": "main",
"index": 0
}
]
]
}
}
}
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This n8n workflow enables you to chat with the uncensored Dolphin Mixtral 8x22B large language model through the Novita AI inference. It provides a streamlined process for sending user messages to the model and returning its responses, making it easy to integrate into chatbots,…
Source: https://n8n.io/workflows/6746/ — 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 integrates a chatbot frontend with a backend powered by Langflow, a visual low-code AI development tool. The flow is triggered whenever a chat message is received via the n8n chatbot wid
pfe-hunter-sophistique. Uses lmChatGroq, chatTrigger, chainLlm, httpRequest. Chat trigger; 24 nodes.
Use cases are many: Compare costs across different models, plan your AI budget, optimize prompts for cost efficiency, or track expenses for client billing! OpenRouter charges a platform fee on top of
This workflow contains community nodes that are only compatible with the self-hosted version of n8n.
Generate Videos from Chat with Google Vertex AI (Veo3) - Beginner Friendly