After GPT-4.1 was released, we transitioned 70k of our Assistants from GPT-4o to GPT-4.1. Our use case heavily relies on the Assistant API combined with RAG.
Since making this update, we’ve encountered significant issues: Assistants are responding with irrelevant content, and the original source citations are no longer being provided.
Even after reverting from GPT-4.1 back to GPT-4o, the problem persists—our Assistants still fail to correctly reference and respond based on RAG data.
Is there currently a known issue affecting the Assistant API?
Given the scale of our deployment and the reliance of our extensive user base, this is an urgent and critical problem for us. We appreciate your immediate attention and prompt resolution.
I’m facing the same issue — GPT-4.1 (both “mini” and “nano”) stubbornly refuse to see or work with files properly. This is currently a blocker for me, as I’m a beginner developer and chose to use 4.1-nano for my project mainly due to its affordability.
Really hoping this gets fixed in the next update. For now, I’ll stick with 4o-mini
I’m seeing the same issue as well, when using any GPT-4.1 models, it doesn’t seem to search the attached files at all in the assistant API, using playground or not.
i created an assistant with the dashboard. in playground and in my own gui 4.1 doesnt seem to acknowledge my RAG document. i get good answers from 4.1mini, 4.1nano and older models. 4.1 quotes from an imaginary document. is it a known issue? does 4.1 not work properly for others? thanks in advance
