GPT-5.6 gets an 18% token-efficiency fix as OpenAI brings back 5-hour limits

kimmonismus · x · 2026-07-29

A user says the 5-hour rate limits are back, after enjoying unlimited use for a while. In the quoted reply, another poster says OpenAI made a reset and a fix that should make GPT-5.6 about 18% more token-efficient.

The reaction is mixed: the efficiency gain is welcome, but the return of limits makes the experience feel worse. The poster also wonders how much the repeated resets are costing OpenAI, joking that the bill must be in the millions.

Related event: OpenAI Resets Codex Limits and Investigates GPT-5.6 Sol Quota Drain(7 posts)→

Original post →

More from Models

Models channel →