Multiple chat model nodes VS. single chat model for every agent

Describe the problem/error/question

I’m building a kind of long workflow that uses several Agent nodes to perform different actions and I was wondering if is there any real difference on reusing the same chat model node in all the Agent nodes or it is irrelevant and is a matter of organization style to have one single node vs. one node per agent (supposing I explicitly do not want to use different models between the agents, of course).

I’m not sure if maybe using one chat model node per Agent node could have some impact on the runtime performance due to some initialization on each model or similar.

Information on your n8n setup

  • n8n version: 1.121.3
  • Database (default: SQLite): SQLite
  • n8n EXECUTIONS_PROCESS setting (default: own, main): own
  • Running n8n via (Docker, npm, n8n cloud, desktop app): cloud
  • Operating system: MacOS

Hi @r-moret, I believe there is no difference whether you use sepaerate sub-nodes or share the same one. To me it is purely organisation and less work to re-use the same nodes (less cluttered), unless of course you have a use case where one of the sub agents might need a different model over the other like open ai vs claude.

1 Like