Is OpenAI silently routing GPT‑6 requests to GPT‑4o?

Posted by skaiuijing 18 hours ago

Counter2Comment3OpenOriginal

I’ve selected GPT‑6, but the responses clearly match GPT‑4o’s behavior.

Is OpenAI’s model router performing silent fallback under load?

Has anyone else observed inconsistent routing or degraded model quality recently?

Comments

Comment by atleastoptimal 2 hours ago

4o is like 40 years old in LLM terms.

Comment by 13 hours ago

Comment by sejje 5 hours ago

If it's clear, why are you asking?

Comment by MeetingsBrowser 18 hours ago

> clearly match GPT‑4o’s behavior

How can you tell?

Comment by installiskeycon 15 hours ago

[dead]