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

2 points by skaiuijing ↗ HN
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?

6 comments

[ 1804 ms ] story [ 370 ms ] thread
I will say I’ve had wildly varying experiences with it. Sometimes it’s amazing. Other times it does feel somewhat “last gen”.. it’s so hard to know for sure though.
If it's clear, why are you asking?
Hardly think so, 6 is exceptionally good at 3d modeling and visuals.