Hub/Models/xiaomi/mimo-v2.5
xiaomitext + audio + image + video → text

Xiaomi: MiMo-V2.5

Canonical ID: xiaomi/mimo-v2.5

Compare ModelOpen on OpenRouter →

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

Verified
No standardized Artificial Analysis benchmark scores recorded for this variant yet.

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.40
Input
Completion Output (1M Tokens)
$2.00
Output
Prompt KV-Cache Read (1M Tokens)
$0.08
Cached
Context Window Capacity
976.563k tokens
Context

Supported Parameters & Features

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p