TPSTokens Per Second

MiMo-V2.5

Xiaomi🇨🇳 China
active
Compare with other models →
Context window1049K tokens
Input / 1M tokens$0.4
Output / 1M tokens$2

Version History

v2.5minor

MiMo-V2.5 introduces a 1,048,576 token context window and claims improved multimodal perception over MiMo-V2-Omni. Xiaomi positions it as delivering Pro-level agentic performance at approximately half the inference cost of comparable models.

Coverage

model releaseXiaomi

Xiaomi Launches MiMo-V2.5 With 1M Context Window at $0.40 per Million Input Tokens

Xiaomi released MiMo-V2.5 on April 22, 2026, a native omnimodal model with a 1,048,576 token context window. The model is priced at $0.40 per million input tokens and $2 per million output tokens, positioning it as a cost-efficient alternative for agentic applications requiring multimodal perception across image and video understanding.

2 min read
xiaomimimo-v2-5omnimodal