Publish time
2026/9/21Model Series
MiMoInput type
Output type
Input Price
¥3 / 1M tokensOutput Price
¥6 / 1M tokensCache Write Price
¥3.75 / 1M tokensCache Read Price
¥0.025 / 1M tokensContext Window
1,000,000Max Output Length
128,000MiMo-V2.6-Pro 是小米自主研发的旗舰级基础模型。该模型参数规模超过 1 万亿(1T),旨在突破应对高难度任务的能力极限。它具备 100 万 token 的上下文窗口及原生多模态能力,并针对智能体(Agent)工作流进行了深度优化;在代码编程、视觉处理、通用任务及科研探索等场景下均展现出顶尖性能,尤其擅长处理复杂且长周期的任务,并在各类智能体应用框架中表现出强大的泛化能力。
Zhinao API routes requests to the best-fit provider and automatically fails over to the one with highest availability.
TTFT
7.80s
Throughput
34.08tps
Uptime
100.00%
Provider Model
nc/xiaomi/mimo-v2.6-pro
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
1,000,000
Max Output
128,000
Input Price
¥3 / 1M tokens
Output Price
¥6 / 1M tokens
Cache Write
¥3.75 / 1M tokens
Cache Read
¥0.025 / 1M tokens
TTFT
10.64s
Throughput
20.80tps
Uptime
100.00%
Provider Model
openrouter/xiaomi/mimo-v2.6-pro
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
1,000,000
Max Output
128,000
Input Price
¥3 / 1M tokens
Output Price
¥6 / 1M tokens
Cache Write
¥3.75 / 1M tokens
Cache Read
¥0.025 / 1M tokens
Compare different providers across Zhinao API
25.39 tok/s
9.48 s
Uptime for xiaomi/mimo-v2.6-pro across all providers
Zhinao API normalizes requests and responses across providers for you
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.360.cn/v1",
apiKey: process.env.ZHINAO_API_KEY,
});
const response = await client.chat.completions.create({
model: "xiaomi/mimo-v2.6-pro",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
temperature: 0.7,
max_tokens: 1000,
});
console.log(response.choices[0].message.content);