text·image·video
Kimi K2.7 Code Highspeed
silvamux/
kimi-k2.7-code-highspeedKimi K2.7 Code Highspeed的主要优势是文本理解与信息检索/RAG,并支持图像、视频信息输入。在文档分析、信息抽取与复杂语义理解中,它能够承担信息理解、分析和结果生成等关键环节。
Pricing
Tune and Pro share the same prices.
| Input context | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| - | ¥13 / 1M tokens | ¥54 / 1M tokens | ¥2.6 / 1M tokens | ¥13 / 1M tokens |
Capabilities
Kimi K2.7 Code Highspeed 综合得分 84,表现优秀,是一款速度与代码能力兼备的模型。文本理解(95%)、信息检索 / RAG(93%)与代码理解与调试(93%)表现突出,既能快速响应又能读懂并修复代码,在高频代码研发场景中优势明显。相对而言,智能体协同(51%)一般,多步骤工具编排任务需适当拆解。高频代码迭代场景越能体现它的速度价值。
84/ 100
专项进阶能力
8 items智能体协同51%
7 questions · 主/客观混合
代码生成80%
10 questions · 客观
代码理解与调试93%
12 questions · 主观
创意写作86%
17 questions · 主观
信息检索 / RAG93%
13 questions · 主/客观混合
数学与科学推理86%
14 questions · 客观
长文本处理93%
3 questions · 主观
多语言能力90%
10 questions · 主/客观混合
通用基础能力
3 items通识知识77%
15 questions · 主/客观混合
文本理解95%
5 questions · 主观
逻辑推理76%
20 questions · 主/客观混合
安全与合规能力
2 items幻觉控制82%
9 questions · 主观
指令遵循87%
14 questions · 主观
Performance
Kimi K2.7 Code Highspeed
kimi-k2.7-code-highspeedLast 24 hours · 99,942 requests
- First token · TTFT · P50
- 1918ms P95 2394 ms
- Output speed · TPS · P50
- 87tok/s P95 99 tok/s
- Full response · E2E · P50
- 7.76s P95 7.90 s
- Request success rate
- 97.12% 97,062 completed requests
24-hour availability
24 hours ago12 hours agoNow
Kimi K2.7 Code Highspeed example code and API
Pro
kimi-k2.7-code-highspeed/api/v0/chat/completions/api/v1/chat/completions/api/anthropic/v1/messagescurl https://www.silvamux.com/api/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k2.7-code-highspeed",
"messages": [{"role": "user", "content": "Hello, please introduce yourself"}]
}'# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://www.silvamux.com/api/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="kimi-k2.7-code-highspeed",
messages=[
{"role": "user", "content": "Hello, please introduce yourself"}
],
)
print(response.choices[0].message.content)// Gradle: implementation(__HL_SLOT_0__)
import okhttp3.*;
OkHttpClient client = new OkHttpClient();
MediaType json = MediaType.get("application/json");
String payload = "{\"model\":\"kimi-k2.7-code-highspeed\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello, please introduce yourself\"}]}";
Request request = new Request.Builder()
.url("https://www.silvamux.com/api/v1/chat/completions")
.header("Authorization", "Bearer YOUR_API_KEY")
.post(RequestBody.create(payload, json))
.build();
try (Response response = client.newCall(request).execute()) {
System.out.println(response.body().string());
}// npm install openai
import OpenAI from 'openai'
const client = new OpenAI({
baseURL: 'https://www.silvamux.com/api/v1',
apiKey: 'YOUR_API_KEY',
})
const response = await client.chat.completions.create({
model: 'kimi-k2.7-code-highspeed',
messages: [{ role: 'user', content: 'Hello, please introduce yourself' }],
})
console.log(response.choices[0].message.content)