text
Glm 5
silvamux/
glm-5GLM 5面向企业知识检索、资料问答与检索增强生成提供稳定的模型能力,优势集中在信息检索/RAG和数学与科学推理。适合需要兼顾任务理解与结果质量的产品和研发团队。
Pricing
Tiers are determined by the input context length of each request; Tune and Pro share the same tiered prices.
| Input context | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| ≤ 32.768K tokens | ¥4 | ¥18 | ¥1 | ¥0 |
| > 32.768K tokens | ¥6 | ¥22 | ¥1.5 | ¥0 |
Capabilities
GLM-5 综合得分 81,表现优秀,是一款综合能力均衡的模型。信息检索 / RAG(94%)、数学与科学推理(93%)与代码生成(90%)表现突出,能从多来源资料提取信息、进行严谨推理并输出可用代码,在高准确率专业场景中优势明显。相对而言,智能体协同(49%)较弱,多步骤工具编排能力一般。推理与检索并重的任务越能体现它的价值。
81/ 100
专项进阶能力
8 items智能体协同49%
7 questions · 主/客观混合
代码生成90%
10 questions · 客观
代码理解与调试80%
12 questions · 主观
创意写作78%
17 questions · 主观
信息检索 / RAG94%
13 questions · 主/客观混合
长文本处理73%
3 questions · 主观
数学与科学推理93%
14 questions · 客观
多语言能力88%
10 questions · 主/客观混合
通用基础能力
3 items通识知识76%
15 questions · 主/客观混合
文本理解83%
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86%
9 questions · 主观
指令遵循86%
14 questions · 主观
Performance
Glm 5 Tune
glm-5@tuneLast 24 hours · 75,955 requests
- First token · TTFT · P50
- 591ms P95 1212 ms
- Output speed · TPS · P50
- 97tok/s P95 100 tok/s
- Full response · E2E · P50
- 4.12s P95 9.83 s
- Request success rate
- 99.54% 75,603 completed requests
24-hour availability
24 hours ago12 hours agoNow
Glm 5
glm-5Last 24 hours · 81,776 requests
- First token · TTFT · P50
- 1601ms P95 1750 ms
- Output speed · TPS · P50
- 87tok/s P95 97 tok/s
- Full response · E2E · P50
- 7.13s P95 9.40 s
- Request success rate
- 98.14% 80,253 completed requests
24-hour availability
24 hours ago12 hours agoNow
Glm 5 example code and API
Tune
glm-5@tune/api/v0/chat/completions/api/v1/chat/completions/api/anthropic/v1/messagesPro
glm-5/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": "glm-5",
"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="glm-5",
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\":\"glm-5\",\"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: 'glm-5',
messages: [{ role: 'user', content: 'Hello, please introduce yourself' }],
})
console.log(response.choices[0].message.content)