小米大模型mimo-v2-flash简单接触

skywalk81632026-01-03 10:31

模型详细信息

模型名称	`mimo-v2-flash`
上下文长度	256 K
最大输出长度	128 K
模型能力	深度思考、流式输出、函数调用、结构化输出
价格	输入、输出限时免费
流控	RPM: 100 TPM: 暂无限制

OpenAI API 兼容

请求地址

复制代码

https://api.xiaomimimo.com/v1/chat/completions

请求头

接口支持以下两种认证方式，请选择其中一种添加到请求头中：

方式一：api-key 字段认证，格式：
复制代码
```
api-key: $MIMO_API_KEY
Content-Type: application/json
```

方式二：Authorization: Bearer 认证，格式：

复制代码

Authorization: Bearer $MIMO_API_KEY
Content-Type: application/json

API调用信息：

api-key:xxxx

base_url: https://api.xiaomimimo.com/v1

模型：mimo-v2-flash

复制代码

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-flash",
    messages=[
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": "please introduce yourself"
        }
    ],
    max_completion_tokens=1024,
    temperature=0.3,
    top_p=0.95,
    stream=False,
    stop=None,
    frequency_penalty=0,
    presence_penalty=0,
    extra_body={
        "thinking": {"type": "disabled"}
    }
)

print(completion.model_dump_json())