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

Posted by skaiuijing on Monday September 07, 2026 @09:49AM
from the self-post dept.

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?

( 5 comments | 2 points | on HN )

Re:Is OpenAI silently routing GPT‑6 requests to GPT‑4o? by MeetingsBrowser on Monday September 07, 2026 @09:53AM (#49598479)

> clearly match GPT‑4o’s behavior

How can you tell?

[ Parent | on HN ]

Re:Is OpenAI silently routing GPT‑6 requests to GPT‑4o? by installiskeycon on Monday September 07, 2026 @12:55PM (#49600392)

LISTON

[ Parent | on HN ]

Re:Is OpenAI silently routing GPT‑6 requests to GPT‑4o? by sejje on Monday September 07, 2026 @10:50PM (#49605197)

If it's clear, why are you asking?

[ Parent | on HN ]

Re:Is OpenAI silently routing GPT‑6 requests to GPT‑4o? by atleastoptimal on Tuesday September 08, 2026 @01:33AM (#49605879)

4o is like 40 years old in LLM terms.

[ Parent | on HN ]

Re:Is OpenAI silently routing GPT‑6 requests to GPT‑4o? by sshussain270 on Wednesday September 09, 2026 @03:13AM (#49622470)

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

[ Parent | on HN ]