Publish time
2026/9/21Model Series
MiMoInput type
Output type
Input Price
¥1 / 1M tokensOutput Price
¥2 / 1M tokensCache Write Price
¥1.25 / 1M tokensCache Read Price
¥0.02 / 1M tokensContext Window
1,000,000Max Output Length
128,000MiMo-V2.6-Flash 是由小米开发的开源基础模型。该模型基于“混合专家”(Mixture-of-Experts)架构构建,总参数量达 3090 亿,每个 Token 激活参数量为 150 亿,并采用混合注意力机制以提升计算效率。它具备 100 万 Token 的上下文窗口及原生多模态能力。该模型针对智能体(Agent)工作流进行了优化,在编程、视觉、通用及研究等场景下表现出色,尤其擅长处理复杂的长程任务,并在多种智能体框架下展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
0.53s
Throughput
34.10tps
Uptime
91.00%
Provider Model
nc/xiaomi/mimo-v2.6-flash
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
1,000,000
Max Output
128,000
Input Price
¥1 / 1M tokens
Output Price
¥2 / 1M tokens
Cache Write
¥1.25 / 1M tokens
Cache Read
¥0.02 / 1M tokens
TTFT
0.70s
Throughput
21.60tps
Uptime
100.00%
Provider Model
openrouter/xiaomi/mimo-v2.6-flash
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
1,000,000
Max Output
128,000
Input Price
¥1 / 1M tokens
Output Price
¥2 / 1M tokens
Cache Write
¥1.25 / 1M tokens
Cache Read
¥0.02 / 1M tokens
Compare different providers across Zhinao API
31.43 tok/s
0.58 s
Uptime for xiaomi/mimo-v2.6-flash 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-flash",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
temperature: 0.7,
max_tokens: 1000,
});
console.log(response.choices[0].message.content);