by Xiaomi
MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architecture. MiMo-V2-Flash supports a hybrid-thinking toggle and a 256K context window, and excels at reasoning, coding, and agent scenarios. On SWE-bench Verified and SWE-bench Multilingual, MiMo-V2-Flash ranks as the top #1 open-source model globally, delivering performance comparable to Claude Sonnet 4.5 while costing only about 3.5% as much. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config).
| Signal | Strength | Weight | Impact |
|---|---|---|---|
| Recency2026-03-03T20:24:47.053Z | 100 | 15% | +15.0 |
| Capabilities2026-03-03T20:24:47.053Z | 57 | 25% | +14.3 |
| Context Window2026-03-03T20:24:47.053Z | 86 | 15% | +12.9 |
| Output Capacity2026-03-03T20:24:47.053Z | 80 | 10% | +8.0 |
| Versatility2026-03-03T20:24:47.053Z | 33 | 10% | +3.3 |
| Pricing Tier2026-03-03T20:24:47.053Z | 0 | 25% | +0.1 |
Cost Estimator
You save $39.29/month vs category average