Vibeleaderboard
← All Intel
Intel / post

Inception ships Mercury 3 with claimed 1000+ tokens per second

Source
x.com
Date
Inception@_inception_ai

Don't blink. You may miss it. Mercury 3, 1000+ toks/s, available now 🤠

Why it matters

Inception says its Mercury 3 model is available now and generates over 1000 per second. If the claim holds, latency-sensitive loops and coding workflows could run far faster. Quality and pricing are not given in the post.

Terms in this piece · Glossary
  • token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
  • benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
  • AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
More from Inception
Recommended reads
Comments

Checking sign-in…

Loading comments…