MiMo-V2-Omni

MiMo-V2-Omni is Xiaomi's omni foundation model uniting frontier multimodal understanding with strong agentic capability. It fuses dedicated image, video, and audio encoders into a single shared backbone, processing all modalities simultaneously. Natively supports structured tool calling, function execution, and UI grounding. Supports over 10 hours of continuous audio understanding and 256K token context window. It is served by xiaomi with a 256K-token context window at $0.4 / $2 per 1M input/output tokens.