MiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture. It combines strong multimodal perception with agentic capability — visual grounding, multi-step planning, tool use, and code execution — making it well-suited for complex real-world tasks that span modalities. 256K context window. · Succeeded by mimo-v2.5
function_calling| Model | Max chars | Sample rate | Voices | Languages | Pricing |
|---|---|---|---|---|---|
| MiMo-v2-tts | — | — | — | — | — |
| MiMo-v2.5-asr | — | — | — | — | — |
| MiMo-v2.5-tts-voiceclone | — | — | — | — | — |
| MiMo-v2.5-tts-voicedesign | — | — | — | — | — |
| MiMo-v2.5-tts | — | — | — | — | — |
| MiMo-V2-Flash | — | — | — | — | $0.1$0.3 |
| MiMo-v2.5 | — | — | — | — | $0.14$0.28 |
| mimo-v2.6-flash | — | — | — | — | $0.14$0.28 |
| MiMo-V2-Omni | — | — | — | — | $0.4$2 |
| MiMo-v2.5-pro | — | — | — | — | $0.44$0.87 |
| mimo-v2.6-pro | — | — | — | — | $0.44$0.87 |
| MiMo-V2-Pro | — | — | — | — | $1$3 |
| mimo-v2.6-pro-ultraspeed | — | — | — | — | $4.35$8.7 |
/v1/models/xiaomi/MiMo-V2-OmniMiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture. It combines strong multimodal perception with agentic capability — visual grounding, multi-step planning, tool use, and code execution — making it well-suited for complex real-world tasks that span modalities. 256K context window.