Updated 5/11/2026
Xiaomi's 310B parameter multimodal model with native understanding of text, image, video, and audio.
相比于纯文本的 Pro 版本，标准版 V2.5 主打极速推理与多模态原生理解。它能够像人一样直接看图、看视频、听声音，非常适合需要多媒体处理能力的应用。
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)The following platforms provide free access to Mimo V2.5 (Đa phương thức) through free tiers, trial credits, or daily quotas.
| Provider | Context Window | Free Quota | Requires CC | Trust | Action |
|---|---|---|---|---|---|
| Xiaomi | N/A | $2/mo | No | Trust 90 | Details |
Yes. Mimo V2.5 (Đa phương thức) is available for free through 1 provider(s) listed below, with no purchase required.
Free access varies by provider — Xiaomi: Monthly Credits.
Sign up with Xiaomi, then create an API key from your dashboard. See the provider details above for the exact steps.
Mimo V2.5 (Đa phương thức) is currently available for free via: Xiaomi.
Help the community by sharing other ways to access this model for free.