xiaomi logo

Xiaomi

MiMo-V2.5

MiMo-V2.5 is a native omnimodal model by Xiaomi.

At a glance

Input / 1M
$0.14
Output / 1M
$0.28
Context
1.05M
Max output
131K
Intelligence
25.2
Released
Apr 2026
Text inputAudio inputImage inputVideo inputReasoningTool calling

Pricing

MiMo-V2.5 API pricing

Per-token rates, plus what common tasks actually cost.

Input tokensPer 1M tokens$0.14
Output tokensPer 1M tokens$0.28
Cached input (read)Per 1M tokens$0.00
Cache writePer 1M tokensNot available

Chat message

2K in, 500 out

$0.42

per 1,000 requests

Coding task

30K in, 4K out

$5.32

per 1,000 requests

Long document summary

150K in, 2K out

$21.56

per 1,000 requests

Benchmarks

MiMo-V2.5 benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

25.2

Coding index

56.8

Agentic index

15.8

Specs

Context window and capabilities

What it can read, what it can write, and which API features it supports.

Context window
1.05M tokens
Max output
131K tokens
Input types
Audio, Image, Text, Video
Output types
Text
Reasoning effort
Not available
Release date
April 22, 2026
  • Tool calling
  • Structured outputs
  • JSON mode
  • Reasoning
  • Temperature
  • Stop sequences
  • Deterministic seed
  • Verbosity control

FAQ

Frequently asked questions

How much does MiMo-V2.5 cost?

MiMo-V2.5 costs $0.14 per 1M input tokens and $0.28 per 1M output tokens through the API. A typical chat message costs about $0.42 per 1,000 messages.

What is the context window of MiMo-V2.5?

MiMo-V2.5 accepts up to 1.05M tokens of input and can write up to 131K tokens in a single response.

What is the best alternative to MiMo-V2.5?

MiMo-V2.6-Flash from Xiaomi is a strong alternative. It offers: higher intelligence score, newer release.

Can I use MiMo-V2.5 alongside other models?

Yes. Shortcut Chat sends one prompt to MiMo-V2.5 and any other models you pick at the same time, so you can compare answers side by side.

xiaomi logo

Try MiMo-V2.5 next to every other model.

Use MiMo-V2.5 alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.