A 750 tok/s demo highlights OpenAI’s fastest available model on OpenRouter

TheZachMueller · x · 2026-07-24

The poster shared a visualization of 750 tok/s, framing it as a speed demo for OpenAI’s smartest available model.

The thread is about raw model throughput rather than app-level usage: the claim is that the model is faster than anything currently available on OpenRouter, and the visual is meant to highlight that speed in a playful way.

Original post →

More from Models

Models channel →