MiMo v2 Omni

MiMo v2 Omni is Xiaomi's flagship model in the MiMo family, representing the company's entry into large-scale multimodal AI. As a proprietary model from the Chinese technology company, it positions Xiaomi alongside other tech giants offering comprehensive AI solutions beyond their traditional hardware focus. The model supports four modalities—text, image, audio, and video—making it one of the more comprehensive multimodal offerings available. With a 262,144 token context window, it can process substantial amounts of content across these different input types. However, the model does not include tool calling capabilities, which distinguishes it from many other flagship models that emphasize agentic workflows. MiMo v2 Omni appears designed for applications requiring rich media understanding and generation, particularly in consumer and enterprise scenarios where Xiaomi's ecosystem integration might provide advantages. Its multimodal capabilities make it suitable for content analysis, media processing, and applications that need to reason across different types of input simultaneously.