# 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).

## Model Information

- **Organization**: [Xiaomi](/llm.txt)
- **Slug**: mimo-v2-flash
- **Available at Providers**: 32
- **Release Date**: December 16, 2025

### Benchmark Scores
- Weekly: 0.67
- AIME 2025: 0.941
- HLE: 0.221
- GPQA: 0.837
- SWE Bench: 0.734
- Terminal: 0.305
- Browsecomp: 0.583

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [AIHubMix](/llm/aihubmix.txt) | mimo-v2-flash | 0.19 | 0.58 |  | [View](https://aihubmix.com/model/mimo-v2-flash) |
| [AIHubMix](/llm/aihubmix.txt) | mimo-v2-flash-free | 0.00 | 0.00 | Yes | [View](https://aihubmix.com/model/mimo-v2-flash-free) |
| [AIMLAPI](/llm/aimlapi.txt) | MiMo V2 Flash | 0.11 | 0.33 |  |  |
| [Xiaomi](/llm/xiaomi.txt) | MiMo-V2-Flash | 0.07 | 0.21 |  |  |
| [Novita AI](/llm/novita.txt) | mimo-v2-flash | 0.10 | 0.30 |  |  |
| [Hugging Face](/llm/huggingface.txt) | MiMo-V2-Flash | 0.10 | 0.30 |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | MiMo V2 Flash |  |  |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | MiMo V2 Flash (Thinking) |  |  |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | MiMo V2 Flash Original |  |  |  |  |
| [OpenRouter](/llm/openrouter.txt) | MiMo-V2-Flash | 0.09 | 0.29 |  | [View](https://openrouter.ai/xiaomi/mimo-v2-flash-20251210) |
| [ValorGPT](/llm/valorgpt.txt) | XI |  |  | Yes | [View](https://www.valorgpt.com/models/xiaomi-mimo-v2-flash-free) |
| [Vercel AI Gateway](/llm/vercel.txt) | MiMo V2 Flash | 0.10 | 0.30 |  |  |
| [Yupp](/llm/yupp.txt) | MiMo V2 Flash (Chutes AI) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | XiaomiMiMo/MiMo-V2-Flash (Novita) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | MiMo V2 Flash (OpenRouter) |  |  |  |  |
| [ZenMUX](/llm/zenmux.txt) | Xiaomi: MiMo-V2-Flash Free | 0.00 | 0.00 | Yes |  |
| [ZenMUX](/llm/zenmux.txt) | Xiaomi: MiMo-V2-Flash | 0.10 | 0.30 |  |  |
| [Atlas Cloud](/llm/atlascloud.txt) | MiMo V2 Flash | 0.10 | 0.30 |  | [View](https://www.atlascloud.ai/models/xiaomi/mimo-v2-flash) |
| [Kilo Code](/llm/kilocode.txt) | Xiaomi: MiMo-V2-Flash | 0.09 | 0.29 |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | MiMo V2 Flash (Thinking) Original |  |  |  |  |
| [302.AI](/llm/302ai.txt) | xiaomimimo/mimo-v2-flash | 0.10 | 0.30 |  | [View](https://302ai-en.apifox.cn/api-308032503) |
| [Arena AI](/llm/arenaai.txt) |  |  |  |  |  |
| [Jiekou.AI](/llm/jiekou.txt) | XiaomiMiMo/MiMo-V2-Flash | 0.00 | 0.00 | Yes |  |
| [RouterLink](/llm/routerlink.txt) | MiMo V2 Flash |  |  |  |  |
| [Blackbox AI](/llm/blackboxai.txt) | blackboxai/xiaomi/mimo-v2-flash |  |  |  |  |
| [MegaNova](/llm/meganova.txt) | MiMo V2 Flash | 0.10 | 0.30 |  |  |
| [Qiniu](/llm/qiniuai.txt) | Mimo-V2-Flash |  |  |  |  |
| [LangDB](/llm/langdb.txt) | mimo-v2-flash |  |  |  | [View](https://langdb.ai/app/models) |
| [WaveSpeed AI](/llm/wavespeed.txt) | mimo-v2-flash | 0.10 | 0.32 |  |  |
| [Airforce API](/llm/airforce.txt) | mimo-v2-flash |  |  |  |  |
| [Writingmate](/llm/writingmate.txt) | Xiaomi: MiMo-V2-Flash |  |  |  | [View](https://writingmate.ai/models/xiaomi/mimo-v2-flash) |
| [LLM Stats](/llm/llmstats.txt) | MiMo-V2-Flash |  |  |  |  |

---

[← Back to all providers](/llm.txt)