Is OpenAI silently routing GPT‑6 requests to GPT‑4o?
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?
4 threads
4o is like 40 years old in LLM terms.
Hardly think so, 6 is exceptionally good at 3d modeling and visuals.
If it's clear, why are you asking?
> clearly match GPT‑4o’s behavior
How can you tell?