Enterprise DNAEnterprise DNA
LModelsBest vision
X

MiMo-V2.5

by Xiaomi

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 perceptio

M

Models

MiMo-V2.5

Added 10 July 2026

#xiaomi

Overview

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...

How to use / API access

Call via OpenRouter with model id `xiaomi/mimo-v2.5`.

  • openrouter · xiaomi/mimo-v2.5 Docs

OpenRouter id: xiaomi/mimo-v2.5

Benchmarks

  • Intelligence Index (artificial-analysis): 21.8 index
  • Coding Index (artificial-analysis): 56.8 index
  • Agentic Index (artificial-analysis): 15.8 index
  • Design Arena 3d (other): 1217 elo · #42
  • Design Arena asciiart (other): 1145 elo · #46
  • Design Arena codecategories (other): 1261 elo · #36
  • Design Arena dataviz (other): 1250 elo · #34

Notes

MiMo-V2.5 is listed in the EDNA Models directory from the OpenRouter catalogue.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

USAGE / OPENROUTER

How much MiMo-V2.5 is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
447B ▼13.6%
Requests, last 7 days
10.5M
Tool calls, last 7 days
2.6M
Intelligence score
21.8
People's vote
1428
Average cost per request
9.6¢
Price per million tokens
$0.119 in · $0.238 out
0500B1T19 Sept: 841B tokens, 11.2M requests20 Sept: 878B tokens, 11.8M requests21 Sept: 987B tokens, 13.3M requests22 Sept: 695B tokens, 9.8M requests23 Sept: 346B tokens, 5.6M requests24 Sept: 241B tokens, 4.6M requests25 Sept: 188B tokens, 3.9M requests26 Sept: 160B tokens, 3.4M requests27 Sept: 158B tokens, 5.9M requests28 Sept: 167B tokens, 3.5M requests29 Sept: 167B tokens, 3.6M requests30 Sept: 161B tokens, 3.6M requests1 Oct: 161B tokens, 3.1M requests2 Oct: 143B tokens, 2.9M requests3 Oct: 126B tokens, 2.9M requests4 Oct: 123B tokens, 2.4M requests5 Oct: 143B tokens, 2.8M requests6 Oct: 118B tokens, 2.4M requests7 Oct: 95B tokens, 2.1M requests8 Oct: 88.3B tokens, 2M requests9 Oct: 81.5B tokens, 1.8M requests10 Oct: 62.8B tokens, 1.4M requests11 Oct: 58.8B tokens, 1.4M requests12 Oct: 70.6B tokens, 1.7M requests13 Oct: 77.3B tokens, 1.8M requests14 Oct: 77.6B tokens, 1.6M requests15 Oct: 82.2B tokens, 1.8M requests16 Oct: 79.1B tokens, 1.7M requests17 Oct: 67.3B tokens, 1.5M requests18 Oct: 57.9B tokens, 1.4M requests19 Oct: 70.7B tokens, 1.6M requests20 Oct: 74.2B tokens, 1.7M requests21 Oct: 15.2B tokens, 920K requests19 Sept3 Oct17 Oct21 OctSee where it ranks on the leaderboard →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Check the source

Price date: 2026-10-18. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 21.8 (2026-10-18) ↗Coding Index: 56.8 (2026-10-18) ↗Agentic Index: 15.8 (2026-10-18) ↗
Compare this model with alternatives →