All Models
MiMo-V2-Flash
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).
Available Providers (9)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Chutes | XiaomiMiMo/MiMo-V2-Flash | $0.09/MTok | $0.29/MTok | 262.1K | 32K | |
 ZenMux | xiaomi/mimo-v2-flash | $0.10/MTok | $0.30/MTok | 262K | 64K | |
 Xiaomi | mimo-v2-flash | $0.10/MTok | $0.30/MTok | 256K | 64K | |
 OpenRouter | xiaomi/mimo-v2-flash | $0.10/MTok | $0.30/MTok | 262.1K | 65.5K | |
 Vercel AI Gateway | xiaomi/mimo-v2-flash | $0.10/MTok | $0.29/MTok | 262.1K | 32K | |
 Meganova | XiaomiMiMo/MiMo-V2-Flash | $0.10/MTok | $0.30/MTok | 262.1K | 32K | |
 Hugging Face | XiaomiMiMo/MiMo-V2-Flash | $0.10/MTok | $0.30/MTok | 262.1K | 4.1K | |
 NanoGPT | xiaomi/mimo-v2-flash | $0.10/MTok | $0.31/MTok | 256K | 32.8K | |
 Qiniu | mimo-v2-flash | —/MTok | —/MTok | 256K | 256K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output