gpt-5.4-mini warning in Agent Builder, but logs show it’s still being used

API Bugs
1

Hi,

I’m using the Agent Builder with multi-agent workflows (Responses API).

When I open an agent in the Builder, I now see this warning:

“gpt-5.4-mini doesn’t work with the Responses API – We’re using the default model instead.”

However, checking the platform logs shows that requests are still being processed with gpt-5.4-mini.

So it seems like:

  • the warning might be incorrect

  • no actual fallback is happening

This setup worked fine for weeks without any changes on my side.

Questions:

  • Is this a known UI/validation issue in the Agent Builder?

  • Can we rely on logs as the source of truth for the actual model used?

Thanks!

2

Welcome to the dev Community! @michael129

Based on the model documentation, gpt-5.4-mini does list support for the /v1/responses endpoint, which corresponds to the Responses API. So it should be compatible.

It’s possible the warning you’re seeing in Agent Builder is a UI/validation issue rather than an actual fallback, especially if your logs are still showing requests being processed with gpt-5.4-mini.

If you’re able to share a screenshot of where the warning appears in the Builder (e.g., model selection or agent config view), that would help others here take a closer look and compare setups.

~Smith

3

Hi Smith,

thanks for your reply.

Quick update: the warning only appeared yesterday. Today it’s no longer showing in the Agent Builder, and everything seems to be working as expected again.

Combined with the logs (which always showed gpt-5.4-mini being used), this strongly suggests it was just a temporary UI/validation issue rather than an actual model fallback.

Appreciate your help!

~michael