流式和非流式调用有什么区别？

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://api.apiyi.com/v1",
)

stream = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "介绍一下量子计算"}],
    stream=True,
    stream_options={"include_usage": True},   # 不加这行拿不到 usage
    timeout=120,
)

chunks = []
for chunk in stream:
    # 末尾的 usage chunk 里 choices 是空数组，必须先判空
    if chunk.choices and chunk.choices[0].delta.content:
        piece = chunk.choices[0].delta.content
        chunks.append(piece)
        print(piece, end="", flush=True)
    if chunk.usage:
        print(f"\n用量：{chunk.usage.total_tokens} tokens")

full_text = "".join(chunks)   # 需要全文时自己拼

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-your-api-key",
  baseURL: "https://api.apiyi.com/v1",
});

const stream = await client.chat.completions.create({
  model: "gpt-5.4",
  messages: [{ role: "user", content: "介绍一下量子计算" }],
  stream: true,
  stream_options: { include_usage: true },
});

let full = "";
for await (const chunk of stream) {
  const delta = chunk.choices?.[0]?.delta?.content;
  if (delta) {
    full += delta;
    process.stdout.write(delta);
  }
  if (chunk.usage) console.log("\n用量：", chunk.usage.total_tokens);
}

# 非流式：一个完整 JSON
curl https://api.apiyi.com/v1/chat/completions \
  -H "Authorization: Bearer $APIYI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [{"role": "user", "content": "你好"}]
  }'

# 流式：一连串 data: 块，最后是 data: [DONE]
# -N 关闭 curl 自己的缓冲，否则看起来还是"一次性出来的"
curl -N https://api.apiyi.com/v1/chat/completions \
  -H "Authorization: Bearer $APIYI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [{"role": "user", "content": "你好"}],
    "stream": true,
    "stream_options": {"include_usage": true}
  }'