← all models

MiMo-V2.5

xiaomi

openrouter
Parameters 705B* 220B–2.3T · reported
Context 1M 1000000 tokens
Input $0.40 OpenRouter
Output $2.00 OpenRouter
Cache read $0.08 OpenRouter

* This model's size is not published. The figure is the source's own estimate, inside a reported interval of 220B–2.3T · confidence: reported .

Knowledge-probe estimate from the paper's leaderboard (revision v2): the figure is the point estimate, the interval is its 90%% prediction interval.

Accepts

text audio image video

Capabilities

frequency_penalty include_reasoning max_tokens presence_penalty reasoning response_format stop structured_outputs temperature tool_choice tools top_k top_p

Description

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...

The OpenRouter API truncates descriptions — read the full text at the source

Also known as

Every id and name this model has been seen under — for matching it against another catalogue.

openrouter xiaomi/mimo-v2.5 huggingface XiaomiMiMo/MiMo-V2.5 version slug xiaomi/mimo-v2.5-20260422 name Xiaomi: MiMo-V2.5 display name MiMo-V2.5

Identifiers

Vendor
xiaomi
OpenRouter
xiaomi/mimo-v2.5
Hugging Face
XiaomiMiMo/MiMo-V2.5
Version slug
xiaomi/mimo-v2.5-20260422
Released
2026-04-22T16:11:09.000Z
First seen
59 d ago
Last crawled
9 min ago