MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
Xiaomi has launched the MiMo-V2.5-Pro-UltraSpeed model, claiming a record-breaking 1000 tokens per second generation speed for a 1-trillion-parameter model. The service is available via a limited-time API trial for developers and enterprises.
Why it matters
This represents a significant milestone in AI inference efficiency, potentially lowering the latency barriers for large-scale model deployment.
English 简体中文 Blog Join us English 简体中文 June 8, 2026 MiMo-V2.5-Pro-UltraSpeed: Pushing 1T-Parameter Model Generation Speed to 1000 TPS Try it now › Access API › 中文 › 1. Xiaomi MiMo-V2.5-Pro-UltraSpeed: Speed is the Ultimate Edge From the first roaring racer of the combustion age to the sonic boom that shattered the sound barrier, humanity s hunger for speed is written into our very DNA. The speed of AI reasoning is no different — it defines the boundaries of intelligence itself. When a model is fast enough, it ceases to be a tool you wait on and becomes an extension of your own thinking: responding in real time, iterating in an instant, collaborating without friction.
The article is a promotional announcement presented as news, focusing on technical specifications and availability.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in