操作步骤
- 1
登录控制台并创建最小权限 API Key。
- 2
从模型目录选择与 endpoint 匹配的可用模型。
- 3
执行下方最小请求，只要求模型回复 ok。
- 4
回到控制台核对模型、Key、状态和用量。
可复制示例
curl https://deeprelayapi.cloud/v1/chat/completions \
-H "Authorization: Bearer $DEEPRELAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-v4-pro","messages":[{"role":"user","content":"只回复 ok"}]}'import os
from openai import OpenAI
client = OpenAI(base_url="https://deeprelayapi.cloud/v1", api_key=os.environ["DEEPRELAY_API_KEY"])
result = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "只回复 ok"}],
)
print(result.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://deeprelayapi.cloud/v1",
apiKey: process.env.DEEPRELAY_API_KEY,
});
const result = await client.chat.completions.create({
model: "deepseek-v4-pro",
messages: [{ role: "user", content: "只回复 ok" }],
});
console.log(result.choices[0].message.content);验收标准
- HTTP 状态为 200。
- 响应模型与请求一致。
- Dashboard 能看到同一时间的调用记录。