UPDATE: FOUND A SOLUTION → The reason for this not working is because I needed to put the region on us-central1, once I did that it worked with any model I wanted
Describe the problem/error/question
I am trying to use the vertex chat model node and connect it to an AI agent and I want to use the gemini 2.5 flash preview model (listed on Gemini 2.5 Flash | Generative AI on Vertex AI | Google Cloud Documentation)
However I receive an error saying the model is not found, same for gemini 1.5/2 or any other model.
What is the error message (if any)?
No model found called ‘gemini-2.5-flash-preview-05-20’
Please share your workflow
{
“nodes”: [
{
“parameters”: {
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.chatTrigger”,
“typeVersion”: 1.1,
“position”: [
220,
0
],
“id”: “736eff2d-e590-4b92-bf11-e161e6e00310”,
“name”: “When chat message received”,
“webhookId”: “0aa4828f-cd8a-4bc5-a713-a3e89d5aa065”
},
{
“parameters”: {
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.agent”,
“typeVersion”: 2,
“position”: [
440,
0
],
“id”: “6ba934d2-9d7f-4cde-8025-782131aec331”,
“name”: “AI Agent”
},
{
“parameters”: {
“projectId”: {
“__rl”: true,
“value”: “dive-407815”,
“mode”: “list”,
“cachedResultName”: “Dive”
},
“modelName”: “gemini-2.5-flash-preview-05-20”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatGoogleVertex”,
“typeVersion”: 1,
“position”: [
440,
180
],
“id”: “78bcf3f8-84c9-4a1c-a534-42c4d956961e”,
“name”: “Google Vertex Chat Model”,
“credentials”: {
“googleApi”: {
“id”: “OuAOBcnGAmHSQ62I”,
“name”: “Google Service Account account”
}
}
}
],
“connections”: {
“When chat message received”: {
“main”: [
[
{
“node”: “AI Agent”,
“type”: “main”,
“index”: 0
}
]
]
},
“Google Vertex Chat Model”: {
“ai_languageModel”: [
[
{
“node”: “AI Agent”,
“type”: “ai_languageModel”,
“index”: 0
}
]
]
}
},
“pinData”: {},
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: “379d193425f7661943a57a905552cfa2870b9e95bc1af1db348606ed80556ca8”
}
}
(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)
Share the output returned by the last node
Information on your n8n setup
- **n8n version: ** 1.0.7 from the helm repo -
- **Database (default: SQLite): ** Postgresql
- n8n EXECUTIONS_PROCESS setting (default: own, main): own
- Running n8n via (Docker, npm, n8n cloud, desktop app): self host k8s helm chart
- Operating system: linux