MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
Key takeaways
- English简体中文Blog Join us English简体中文 June 8, 2026Mi Mo-V2.5-Pro-Ultra Speed: Pushing 1T-Parameter Model Generation Speed to 1000 TPSTry it now ›Access API ›中文 ›1.
- Today, we are thrilled to release Xiaomi MiMo-V2.5-Pro-UltraSpeed in collaboration with TileRT, breaking the 1000 tokens/s decode speed on a 1-trillion-parameter model for the first time!
- The MiMo-V2.5-Pro-UltraSpeed API launches simultaneously at a limited-time promotional price — 3× the cost of MiMo-V2.5-Pro, but delivering approximately 10× the generation speed! 3× the price, 10× the output experience.
English简体中文Blog Join us English简体中文 June 8, 2026Mi Mo-V2.5-Pro-Ultra Speed: Pushing 1T-Parameter Model Generation Speed to 1000 TPSTry it now ›Access API ›中文 ›1. Xiaomi Mi Mo-V2.5-Pro-Ultra Speed: 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.
Today, we are thrilled to release Xiaomi MiMo-V2.5-Pro-UltraSpeed in collaboration with TileRT, breaking the 1000 tokens/s decode speed on a 1-trillion-parameter model for the first time!
The MiMo-V2.5-Pro-UltraSpeed API launches simultaneously at a limited-time promotional price — 3× the cost of MiMo-V2.5-Pro, but delivering approximately 10× the generation speed! 3× the price, 10× the output experience. (API only; Token Plan not supported.)