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 greater computational efficiency. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers strong performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.
function_calling| Model | Context | Max out | Pricing |
|---|---|---|---|
| MiMo-v2-tts | 8K | 8K | |
| MiMo-v2.5-asr | 8K | 2K | |
| MiMo-v2.5-tts-voiceclone | 8K | 8K | |
| MiMo-v2.5-tts-voicedesign | 8K | 8K | |
| MiMo-v2.5-tts | 8K | 8K | |
| MiMo-V2-Flash | 262K | 66K | $0.1$0.3 |
| MiMo-v2.5 | 1.0M | 131K | $0.14$0.28 |
| mimo-v2.6-flash | 1.0M | 131K | $0.14$0.28 |
| MiMo-V2-Omni | 262K | 66K | $0.4$2 |
| MiMo-v2.5-pro | 1.0M | 131K | $0.44$0.87 |
| mimo-v2.6-pro | 1.0M | 131K | $0.44$0.87 |
| MiMo-V2-Pro | 1.0M | 131K | $1$3 |
| mimo-v2.6-pro-ultraspeed | 1.0M | 131K | $4.35$8.7 |
/v1/models/xiaomi/mimo-v2.6-flash