AItiktak - Token 中转平台

流式输出（Server-Sent Events）允许实时接收模型的生成内容，适用于需要逐字显示的场景。

启用流式

在请求中设置 stream: true 即可启用流式输出

curl -X POST https://api.aitiktak.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-plus",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

流式响应格式

流式响应使用 SSE（Server-Sent Events）格式，每条消息以 data: 开头

data: {"id":"chatcmpl-xxx","choices":[{"delta":{"role":"assistant"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":"你好"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":"！"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":"有什么"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","choices":[{"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Python SDK 示例

from aitiktak import AItiktak

client = AItiktak(api_key="YOUR_API_KEY")

stream = client.chat.completions.create(
    model="qwen-plus",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)