Publish time
2026/6/30Model Series
KimiInput type
Output type
Input Price
¥6.5 / 1M tokensOutput Price
¥27 / 1M tokensCache Write Price
¥8.125 / 1M tokensCache Read Price
¥1.3 / 1M tokensContext Window
262,144Max Output Length
262,144Kimi K2.7 Code 是 Kimi 迄今最智能的 Coding 模型,在长上下文中更可靠地遵循指令,能以更高的成功率完成编程任务,同时支持文本、图片与视频输入,思考模式,对话与 Agent 任务。
Zhinao API routes requests to the best-fit provider and automatically fails over to the one with highest availability.
TTFT
12.76s
Throughput
37.77tps
Uptime
92.00%
Provider Model
tokenmall-cdtx/moonshotai/kimi-k2.7-code
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
262,144
Max Output
262,144
Input Price
¥3.9 / 1M tokens
Output Price
¥16.2 / 1M tokens
Cache Write
¥4.875 / 1M tokens
Cache Read
¥0.78 / 1M tokens
TTFT
6.66s
Throughput
48.52tps
Uptime
100.00%
Provider Model
moonshot/moonshotai/kimi-k2.7-code
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
262,144
Max Output
262,144
Input Price
¥6.5 / 1M tokens
Output Price
¥27 / 1M tokens
Cache Write
¥8.125 / 1M tokens
Cache Read
¥1.3 / 1M tokens
Compare different providers across Zhinao API
44.36 tok/s
9.37 s
Uptime for moonshotai/kimi-k2.7-code 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: "moonshotai/kimi-k2.7-code",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
temperature: 0.7,
max_tokens: 1000,
});
console.log(response.choices[0].message.content);