GPT5 can't use sub-agents

[atlasautomation]

Describe the problem/error/question

I’m trying to build an AI agent that has sub-agents. This works fine with the normal GPT 4.1 models but when switching the model to GPT5 it doesn’t work. The model just got release so maybe that’s not surprising but I thought I’d raise the issue.

What is the error message (if any)?

404 No endpoints found that support tool use. To learn more about provider routing, visit: Provider Routing | Intelligent Multi-Provider Request Routing | OpenRouter | Documentation Troubleshooting URL: MODEL_NOT_FOUND | 🦜️🔗 Langchain

Please share your workflow

Share the output returned by the last node

Information on your n8n setup

• n8n version: 1.105.3
• Database (default: SQLite):
• n8n EXECUTIONS_PROCESS setting (default: own, main):
• Running n8n via (Docker, npm, n8n cloud, desktop app): Cloud
• Operating system:

[fahmiiireza]

Hi there @atlasautomation , that is not a bug from n8n or OpenAI, i have tried using the openAI node straightly and it is doable for the gpt 5 to use tools, so it is more of a problem of OpenRouter, so if you want to use gpt 5 for tool calling then i suggest you to use the openAI node straightly

[atlasautomation]

Thanks, and I also realized that the GPT5-chat model don’t support tool calls, so there’s that as well. I’ve moved over to an openAI node now as you suggested, Openrouter require you to bring your own API key for GPT5 anyway.

[fahmiiireza]

yeah, some models don’t support tool calling, they give this kind of error

tools is not supported in this model.

and you’re welcome btw, please mark my answer as the solution if i help answer your question

Thank you!