CAPABILITIES · 协议 / 模型 / 运维
/v1/chat/completions/v1/responses,流式输出/chat/completions、/responses 简写路径gpt-5.6 等(Responses 与 Chat 双通道)deepseek-v4-flash / proglm-5.3 / 5.3-flashDOCS · 复制即用
curl https://api.csz.asia/v1/chat/completions \
-H "Authorization: Bearer sk-你的密钥" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash-0731",
"messages": [
{"role": "user", "content": "用三句话介绍成作聚合"}
],
"stream": true
}'
curl https://api.csz.asia/v1/responses \
-H "Authorization: Bearer sk-你的密钥" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.6",
"input": "为接口写一段健康检查脚本",
"stream": false
}'
Codex / 兼容 Responses 的客户端,把 base_url 指向
https://api.csz.asia/v1 即可,无需改动其它配置。
from openai import OpenAI
client = OpenAI(
api_key="sk-你的密钥",
base_url="https://api.csz.asia/v1",
)
r = client.chat.completions.create(
model="glm-5.3",
messages=[{"role": "user", "content": "写一个 Nginx 限流配置"}],
)
print(r.choices[0].message.content)
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.CSZ_API_KEY,
baseURL: "https://api.csz.asia/v1",
});
const r = await client.chat.completions.create({
model: "deepseek-v4-flash-0731",
messages: [{ role: "user", content: "解释一下限流与熔断" }],
});
console.log(r.choices[0].message.content);
| 用途 | 端点 |
|---|---|
| 对话 | POST /v1/chat/completions |
| Responses | POST /v1/responses |
| 模型列表 | GET /v1/models |
| 控制台 | gdlr.asia/dashboard |
| 充值订阅 | gdlr.asia/buy |
鉴权:Authorization: Bearer sk-…,亦兼容 x-api-key 头。