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 →
{
"name": "ApexApi \u2014 AI Agent (any model)",
"nodes": [
{
"parameters": {
"content": "## \ud83e\udd16 AI Agent on any model (ApexApi)\n\nAn n8n **AI Agent** powered by any of 120+ models through one OpenAI-compatible key.\n\n### Setup (2 min)\n1. **Get a free API key:** https://apexapi.dev/?ref=n8n-ai-agent-any-model\n2. Open the *ApexApi Chat Model* node \u2192 create an **OpenAI** credential: API Key = your `ak-` key, **Base URL** = `https://api.apexapi.dev/v1`.\n3. Pick any model from https://apexapi.dev/models (e.g. `anthropic/claude-haiku-4-5`) and chat.\n\nPowered by ApexApi \u00b7 https://apexapi.dev",
"height": 420,
"width": 360
},
"id": "aaaa0003-aaaa-aaaa-aaaa-aaaaaaaaaa03",
"name": "ApexApi setup",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-780,
-80
]
},
{
"parameters": {
"options": {}
},
"id": "dddddddd-dddd-dddd-dddd-dddddddddddd",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.1,
"position": [
260,
300
]
},
{
"parameters": {
"options": {}
},
"id": "eeeeeeee-eeee-eeee-eeee-eeeeeeeeeeee",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.7,
"position": [
520,
300
]
},
{
"parameters": {
"model": "anthropic/claude-fable-5",
"options": {}
},
"id": "ffffffff-ffff-ffff-ffff-ffffffffffff",
"name": "ApexApi Chat Model (via OpenAI base URL)",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1,
"position": [
520,
520
],
"notes": "Set the OpenAI credential Base URL to https://api.apexapi.dev/v1 and use your ApexApi ak- key. Then type any ApexApi model slug in Model."
}
],
"connections": {
"When chat message received": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"ApexApi Chat Model (via OpenAI base URL)": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
}
},
"settings": {},
"active": false
}
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
ApexApi — AI Agent (any model). Uses chatTrigger, agent, lmChatOpenAi. Chat trigger; 4 nodes.
Source: https://github.com/apexapi/apexapi-n8n/blob/main/templates/03-ai-agent-any-model/workflow.json — 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.
AI Agent : Google calendar assistant using OpenAI. Uses chatTrigger, lmChatOpenAi, memoryBufferWindow, googleCalendarTool. Chat trigger; 13 nodes.
OpenSea AI-Powered Insights via Telegram. Uses chatTrigger, telegramTrigger, lmChatOpenAi, memoryBufferWindow. Chat trigger; 13 nodes.
Build an MCP server with Airtable. Uses chatTrigger, agent, memoryBufferWindow, mcpClientTool. Chat trigger; 13 nodes.
Build an MCP server with Airtable. Uses chatTrigger, agent, memoryBufferWindow, mcpClientTool. Chat trigger; 13 nodes.
This template is a simple AI Agent that acts as a Google Calendar Assistant. It is designed for beginners to have their "first AI Agent" performing common tasks and to help them understand how it work