代码示例

这里保留“直接可复制”的文档风格，方便你快速验证 Cubicspaces 接口。

Python 聊天

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.cubicspaces.cloud/v1"
)

resp = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "给我一段欢迎语"}]
)

print(resp.choices[0].message.content)

Node.js 图像生成

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CUBICSPACES_API_KEY,
  baseURL: "https://api.cubicspaces.cloud/v1"
});

const image = await client.images.generate({
  model: "gpt-image-1",
  prompt: "A futuristic cubic workspace floating in space"
});

console.log(image.data[0].url);

cURL 视频任务

curl https://api.cubicspaces.cloud/v1/video/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "kling-v2",
    "prompt": "A glass city in the clouds",
    "duration": 5
  }'

流式输出

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CUBICSPACES_API_KEY,
  baseURL: "https://api.cubicspaces.cloud/v1"
});

const stream = await client.chat.completions.create({
  model: "gpt-4o-mini",
  stream: true,
  messages: [{ role: "user", content: "用三句话介绍 Cubicspaces。" }]
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices?.[0]?.delta?.content || "");
}