MiMo-V2.6-Flash
A 9B distill (MiMo-V2.6-Distill-Qwen-9B) was released alongside.
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Input
- text, image, video, audio
- Output
- text
- License
- mit
- Pricing
- input: $0.14 · cached input: $0.0028 · output: $0.28 (per 1M tokens (USD)) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Xiaomi MiMo API | mimo-v2.6-flash | — | docs |
| Hugging Face | — | huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL | — |
Notable capabilities (1)
- 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
Timeline entry
- Xiaomi releases MiMo-V2.6 Pro (1.02T MoE) and Flash under MIT license; Pro becomes the top open-weights model on Artificial Analysis ★★★★
On Sept 21–22, 2026 Xiaomi released the MiMo-V2.6 series under the MIT license: Pro (1.02T total / 42B active MoE), Flash (~311B / 15B active), a Pro-UltraSpeed serving tier and a 9B Qwen distill. Both main models have 1M context and omnimodal input. Pro scored 46 on the Artificial Analysis…
Other Xiaomi models
MiMo-V2.6-Pro · Xiaomi-Robotics-1 (XR-1, 5B) · Xiaomi-Robotics-U0 (38B) / U0-4B · Xiaomi-Robotics-0 (4.7B VLA)