Publish time
-Model Series
Input type
Output type
Context Window
262,144Max Output Length
32,768Input Price
¥4 / 1M tokensOutput Price
¥21 / 1M tokenskimi-k2.5 是 Kimi 迄今最全能的模型,原生的多模态架构设计,同时支持视觉与文本输入、思考与非思考模式、对话与 Agent 任务 模型上下文长度 256k,支持长思考擅长深度推理 支持自动上下文缓存功能,ToolCalls、JSON Mode、Partial Mode、联网搜索功能等能力
Zhinao API routes requests to the best-fit provider and automatically fails over to the one with highest availability.
TTFT
2.66s
Throughput
30.83tps
Uptime
100.00%
Provider Model
qiniu/kimi-k2.5
Supported Parameters
Recent Uptime
Reasoning
-
Supported Response Formats
Request Log Collection
-
Distillable
-
Total Context
4,096
Max Output
2,048
Input Price
¥4 / 1M tokens
Output Price
¥21 / 1M tokens
TTFT
4.31s
Throughput
21.32tps
Uptime
79.00%
Provider Model
moonshot/moonshot/kimi-k2.5
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Request Log Collection
ZDR Supported
Distillable
Yes
Total Context
262,144
Max Output
65,500
Input Price
¥4 / 1M tokens
Output Price
¥21 / 1M tokens
Compare different providers across Zhinao API
28.19 tok/s
2.76 s
Uptime for moonshot/kimi-k2.5 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: "moonshot/kimi-k2.5",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
temperature: 0.7,
max_tokens: 1000,
});
console.log(response.choices[0].message.content);