Free Mimo V2.5 (Multimodal) on Xiaomi

Xiaomi's standard multimodal model.

Updated 5/11/20261 code examples

About the Model

Compared with the Pro version of the plain text, the standard version V2.5 focuses on extreme speed inference and multimodal native understanding. It can directly watch pictures, watch videos, and listen to sounds like people, which is very suitable for applications that require multimedia processing capabilities.

Core strengths and characteristics

Native full modal support: not only understand text, but also directly process images, video frames and audio streams, without the need to transfer through third-party models.
Extreme speed output experience: The exclusive "Native Multiprediction (MTP)" technology and hybrid sliding window attention mechanism (Hybrid Attention) not only save nearly 7 times the memory memory usage, but also make the output speed take off.
Extra Large Context: Like the Pro version, it supports long text inputs up to 1,000,000 (1M) tokens.
Very cost-effective: compared to the flagship version, the input price has dropped significantly (only $0.40 / 1M tokens).

View all free providers for Mimo V2.5 (Đa phương thức)

How to Access for Free (via Xiaomi)

Free basis (Why is it free?)

This is a paid multi-modal model, and we have also passed the new activity for you to get a long-term free test quota:

[Additional benefits] Although this model itself is free, if you also want to experience other paid top models of Xiaomi (such as MIMO V2.5 dialogue model), I am currently using the MIMO open platform, register as a new user through my invitation code, you can get the $2 API Experience gold. • Invitation code: tue76x • Registration link: https://platform.xiaomimimo.com?ref=tue76x • Exchange method: Click the entrance to the lower left of the console to fill in after registration, and the experience bonus Valid for 40 days.

📖 View Full Guide

Try it in your browser

Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.

Code Examples

python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5",
    messages=[
        {
            "role": "user", 
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
                    },
                },
            ],
        }
    ],
)
print(completion.choices[0].message.content)

Community Feedback

Comments are tied to your GitHub account — sign in to join the discussion.