Xiaomi: MiMo-V2.6-Flash
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for... 309B total parameters with 15B active per token 1M-token context window at ultra-budget pricing Open-source MoE design suited to high-throughput inference Lower capability ceiling than the Pro variant New release has limited independent evaluation coverage Budget coding and reasoning Long-context batch processing High-throughput agent backends
Specifications
| Lab | Xiaomi |
|---|---|
| Context window | 1,048,576 |
| Input price | $0.14/1M |
| Output price | $0.28/1M |
| Release | 2026-09-01 00:00:00 |
Strengths
- 309B total parameters with 15B active per token
- 1M-token context window at ultra-budget pricing
- Open-source MoE design suited to high-throughput inference
Weaknesses
- Lower capability ceiling than the Pro variant
- New release has limited independent evaluation coverage
Best for
- Budget coding and reasoning
- Long-context batch processing
- High-throughput agent backends
In Depth: MiMo-V2.6-Flash
Summary
MiMo-V2.6-Flash is an AI model from Xiaomi.
Released 2026-09-01 00:00:00. It supports Text, image, video, audio input and produces Text output, with a context window of 1M tokens. Input pricing is $0.14 per 1M tokens and output is $0.28 per 1M tokens on OpenRouter.