Xiaomi: MiMo-V2.5 API
MiMo-V2.5 is the versatile, high-efficiency backbone of Xiaomi's 2.5-series AI ecosystem. While inheriting the "Harness-Awareness" architecture from the Pro version, MiMo-V2.5 is optimized for lower latency and extreme token efficiency in repetitive, high-frequency autonomous tasks. It excels at managing medium-to-long execution trajectories (up to 100+ tool calls) and maintaining precise context alignment. In comparative testing, it achieved a 50% reduction in token consumption compared to previous generation models like Muse Spark while maintaining superior task success rates. It is the ideal engine for 2026's decentralized AI micro-services and real-time coding assistants.
- Context window: 256,000 tokens
- Max output: 16,384 tokens
- Input: text, image, video, audio
- Output: text, audio
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2026-04-21
- Knowledge cutoff: 2026-02-28
Frequently Asked Questions
What is the context window of MiMo-V2.5?
MiMo-V2.5 supports a context window of up to 256,000 tokens.
Does MiMo-V2.5 support function calling?
Yes. MiMo-V2.5 supports tool / function calling.
Does MiMo-V2.5 support reasoning?
Yes. MiMo-V2.5 is a reasoning-capable model.
What is the knowledge cutoff of MiMo-V2.5?
The knowledge cutoff of MiMo-V2.5 is 2026-02-28.