As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/mimo-v2-6-flash/

# MiMo-V2.6-Flash

Xiaomi, MiMo V2.6 family. Status: current. Type: reasoning model. Released: 2026-09-21. Training cutoff: not published.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Xiaomi MiMo API | `mimo-v2.6-flash` |  | https://mimo.mi.com/ |
| Hugging Face |  |  | https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL |

## Pricing

- Input: $0.14 per 1M tokens
- Cached input: $0.0028 per 1M tokens
- Output: $0.28 per 1M tokens
- Unit as published: per 1M tokens (USD)
- Source: https://venturebeat.com/technology/better-than-deepseek-xiaomis-mimo-v2-6-pro-debuts-as-the-top-open-weights-model-in-the-world-alongside-cheaper-v2-6-flash
- Last checked: 2026-09-29

## Specs

- Input: text, image, video, audio
- Output: text
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Open weights: yes
- Licence: mit

## What it has not seen

- No published training cutoff. Counted from its release (2026-09-21): at least 1,423 AI events since (302 major, 58 historic), as of 2026-11-13.
- Everything since August 2026: https://postcutoff.com/since/2026-08/

## What stands out

- Cheap open omnimodal MoE: ~311B total / 15B active, 1M context, MIT license, at $0.14 / $0.28 per 1M tokens; RL post-training reportedly cost ~$850K. Source: https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL

## Notes

A 9B distill (MiMo-V2.6-Distill-Qwen-9B) was released alongside.


Model page: https://postcutoff.com/m/mimo-v2-6-flash/