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

[skaiuijing]

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?

[atleastoptimal]

4o is like 40 years old in LLM terms.

[sshussain270]

Hardly think so, 6 is exceptionally good at 3d modeling and visuals.

[sejje]

If it's clear, why are you asking?

[MeetingsBrowser]

> clearly match GPT‑4o’s behavior

How can you tell?