Back to all models
xiaomi
xiaomiXiaomi: MiMo-V2.5
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
xiaomi/mimo-v2.5
Context Size
1,048.576K
Input Price
40,000 Ks/M
Output Price
200,000 Ks/M
Architecture
Text
Audio
Image
Video
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningresponse_formatstoptemperaturetool_choicetoolstop_p
Details
TokenizerOther
Max Completion131,072 tokens
Provider Context1,048.576K tokens
ModeratedNo
CreatedApr 22, 2026