Xiaomi: MiMo-V2.5

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...

Modalities

Input

textimageaudiopdf

Output

text

Pricing

Cost per 1 million tokens

Input

$0.48

Output

$2.4

Model Specs

Context Window

262,144

Max Output

128,000

Release Date

2026-04-22

Knowledge Cutoff

2024-12

Capabilities

Reasoning

Tool Calling

Vision

Last Updated: 2026-04-22

Provider: