MiMo-V2.5

Xiaomi released 2026-04-22

$0.175 per million tokens, balanced

DeepSeek V4 Flash 0731 scores higher and costs less — but you would give something up.

+13.8 on the capability index and 40% cheaper ($0.105/M against $0.175/M). What you lose:

  • no audio, image, video input

Capability scores do not measure context length, output ceiling or which inputs a model accepts, so a higher score does not mean a drop-in replacement.

Every price dimension

Input$0.140/M
Output$0.280/M
Cached input$0.0028/M

Independent scores

Intelligence38
Coding56.8
Agentic24.4
LMArena Elo1427.3default

Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.

Best rankings by task

  • dataviz #21of 142 1273
  • website #23of 151 1289
  • codecategories #23of 145 1285
  • uicomponent #24of 140 1285
  • gamedev #25of 144 1278
  • svg #27of 98 1213
  • 3d #30of 136 1259

Capability

Context window1.1M
Max output131K
Input modestext, audio, image, video
Tool useyes
Reasoningoptional

Provenance

Price sourceopenrouter.ai
Fetched2026-08-24
Quality dataverified

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...

Markdown for LLMs