xiaomitext + audio + image + video → text
Xiaomi: MiMo-V2.5
Canonical ID: xiaomi/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...
Artificial Analysis Benchmarks
VerifiedNo standardized Artificial Analysis benchmark scores recorded for this variant yet.
Token Pricing & Economics
Prompt Input (1M Tokens)
Input$0.40
Completion Output (1M Tokens)
Output$2.00
Prompt KV-Cache Read (1M Tokens)
Cached$0.08
Context Window Capacity
Context976.563k tokens
Supported Parameters & Features
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p