Noesion Radarnoesion.ai
Release2026-09-21

Xiaomi released MiMo-V2.6-Pro-UltraSpeed. It is a faster version of its MiMo-V2.6-Pro model. It matches the original in quality. It delivers roughly ten times the output speed. It supports a one million token context window. It handles text, images, video and audio as input. It returns text. It costs $4.35 per million input tokens and $8.70 per million output tokens. It supports tool calling and structured JSON outputs. It is available now.

What changed

MiMo-V2.6-Pro offered the same quality at slower output speed.

What it unlocks

Running agent workflows with faster output while keeping the same model quality.

  • $4.35 per 1M input tokens
  • $8.70 per 1M output tokens
  • 1,048,576 token context window
  • 131,072 max output tokens

Sources

Send this to someone who needs it

Shares the story and its sources. Nothing about you.

What does this mean for your job?

This is the story as everyone gets it. Once a week we send you the version written for your role — what changed, why it matters for the work you actually do, and one thing to try. Free while we tune it.