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
15,750 pts/M
Output Price
42,000 pts/M
Architecture
Text
Audio
Image
Video
Supported Parameters
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Details
TokenizerOther
Provider Context32K tokens
ModeratedNo
CreatedApr 22, 2026