Publish time
2026/4/23Model Series
MiMoInput type
Output type
Context Window
1,048,576Max Output Length
131,100Input Price
¥2.8 / 1M tokensOutput Price
¥14 / 1M tokens原生全模态感知 + 1M 上下文 — 支持图像、视频、音频、文本的原生理解，实现跨模态精准感知与长程推理，综合感知能力跻身行业前沿。 强大的全模态 Agent 能力 — 具备原生 Agent 执行能力，可高效完成浏览、理解、推理与操作等复杂任务，日常任务表现比肩 MiMo V2.5 Pro。 性能与效率兼备 — 在保持领先能力的同时，实现更优的 token 效率，位于性能与效率的 Pareto 前沿。
Zhinao API routes requests to the best-fit provider and automatically fails over to the one with highest availability.
TTFT
1.04s
Throughput
20.59tps
Uptime
100.00%
Provider Model
openrouter/xiaomi/mimo-v2.5
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Request Log Collection
ZDR Supported
Distillable
Yes
Total Context
1,048,576
Max Output
131,100
Input Price
¥2.8 / 1M tokens
Output Price
¥14 / 1M tokens
TTFT
0.61s
Throughput
16.63tps
Uptime
100.00%
Provider Model
ksyun/xiaomi/mimo-v2.5
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Request Log Collection
ZDR Supported
Distillable
Yes
Total Context
1,048,576
Max Output
131,100
Input Price
¥2.8 / 1M tokens
Output Price
¥14 / 1M tokens
Compare different providers across Zhinao API
27.36 tok/s
1.61 s
Uptime for xiaomi/mimo-v2.5 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-v2.5",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
temperature: 0.7,
max_tokens: 1000,
});
console.log(response.choices[0].message.content);