创建模型响应（流式返回）

使用 Responses API 并开启流式返回，实时接收 SSE 事件流。

参考：OpenAI 官方文档

---

请求示例

from openai import OpenAI

client = OpenAI(base_url="https://api000.com/v1", api_key="sk-xxxxxxxxxxxxxxxx")

# 流式返回
with client.responses.stream(
    model="gpt-4.1",
    input=[{"role": "user", "content": "写一首关于秋天的诗"}]
) as stream:
    for text in stream.text_deltas:
        print(text, end="", flush=True)
print()

cURL 原始流

curl https://api000.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxx" \
  -d '{
    "model": "gpt-4.1",
    "stream": true,
    "input": [{"role": "user", "content": "你好"}]
  }'

---

SSE 事件类型

事件	说明
response.created	响应对象创建
response.in_progress	响应生成中
response.output_item.added	新的输出项被添加
response.content_part.added	内容部分被添加
response.output_text.delta	文本增量（主要内容）
response.output_text.done	文本生成完成
response.content_part.done	内容部分完成
response.output_item.done	输出项完成
response.completed	整个响应完成

---

原始事件流示例

event: response.created
data: {"type":"response.created","response":{"id":"resp_xxx","status":"in_progress",...}}

event: response.output_item.added
data: {"type":"response.output_item.added","output_index":0,...}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":"秋","content_index":0,...}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":"天","content_index":0,...}

event: response.output_text.done
data: {"type":"response.output_text.done","text":"秋天的叶子...","content_index":0,...}

event: response.completed
data: {"type":"response.completed","response":{"status":"completed","usage":{...}}}