流式输出

流式输出（Streaming Output） 是指大模型在生成回复时，每产生一个片段就立即推送给调用方，而非等待全部内容生成完毕后一次性返回。降低了首字延迟，用户更快看到响应，提升交互体验。

工作原理如下：

1. 请求发起：调用方发起请求，标识启用流式模式，"stream"字段取值为“True”。
2. 逐步生成：模型逐个 Token 生成内容。
3. 逐块推送：每生成一个片段，通过 SSE（Server-Sent Events）等方式立即推送。
4. 结束标识：全部生成完成后，发送结束标识信号。

快速入门

下面以GLM-5.2模型为例，展示了非思考模式下的流式输出效果。

思考模式下，思考过程也是按照流式输出的。在思考阶段，"reasoning_content"字段是模型思考的内容，"content"字段为空（回复内容内容为空）；当思考结束后，"content"字段才会有值。

import requests
import json
if __name__ == '__main__':
    url = "https://api-ap-southeast-1.modelarts-maas.com/v2/chat/completions"  # API地址
    api_key = "MAAS_API_KEY"  # 把MAAS_API_KEY替换成已获取的API Key
    # Send request.
    headers = {
        'Content-Type': 'application/json',
        'Authorization': f'Bearer {api_key}'
    }
    data = {
         "model": "glm-5.2",  # model参数
         "messages": [
             {"role": "system", "content": "You are a helpful assistant."},
             {"role": "user", "content": "你好"}
         ],
        "thinking": {
            "type": "disabled"
         },
         "stream": True
     }
    response = requests.post(url, headers=headers, data=json.dumps(data), verify=False)
    # Print result.
    print(response.status_code)
    print(response.text)

curl -X POST "https://api-ap-southeast-1.modelarts-maas.com/v2/chat/completions" \   
-H "Content-Type: application/json" \   
-H "Authorization: Bearer $MAAS_API_KEY" \   
-d '{     
    "model": "glm-5.2",     
    "messages": [       
        {"role": "system", "content": "You are a helpful assistant."},     
        {"role": "user", "content": "你好"}    
    ],
    "thinking": {
        "type": "disabled"
     },
    "stream": true
}'

from openai import OpenAI
import httpx

base_url = "https://api-ap-southeast-1.modelarts-maas.com/openai/v1/chat/completions"  # API地址
api_key = "MAAS_API_KEY"  # 把MAAS_API_KEY替换成已获取的API Key

client = OpenAI(api_key=api_key, base_url=base_url, http_client=httpx.Client(verify=False))
response = client.chat.completions.create(
    model="glm-5.2",
    messages=[
        {"role": "system", "content": "You are a helpful assistant"},
        {"role": "user", "content": "你好"},
    ],
    chat_template_kwargs = {
        "thinking": False
    },
    stream=True
)
for chunk in response:
    if not chunk.choices:
        continue

    print(chunk.choices[0].delta.content, end="")

流式输出的响应：

ata: {"id":"4dc9cd5407fa4fcf92e5d547984819fd","object":"chat.completion.chunk","created":1784770930,"model":"glm-5.2","choices":[{"index":0,"delta":{"role":"assistant","content":"你好"}}],"service_tier":"default","first_token_return_time":1784770931.0727186}

data: {"id":"4dc9cd5407fa4fcf92e5d547984819fd","object":"chat.completion.chunk","created":1784770930,"model":"glm-5.2","choices":[{"index":0,"delta":{"role":"assistant","content":"！有什么"}}],"service_tier":"default","first_token_return_time":1784770931.0729105}

data: {"id":"4dc9cd5407fa4fcf92e5d547984819fd","object":"chat.completion.chunk","created":1784770930,"model":"glm-5.2","choices":[{"index":0,"delta":{"role":"assistant","content":"我可以帮你的"}}],"service_tier":"default","first_token_return_time":1784770931.1312485}

data: {"id":"4dc9cd5407fa4fcf92e5d547984819fd","object":"chat.completion.chunk","created":1784770930,"model":"glm-5.2","choices":[{"index":0,"delta":{"role":"assistant","content":"吗？"}}],"service_tier":"default","first_token_return_time":1784770931.1887114}

data: {"id":"4dc9cd5407fa4fcf92e5d547984819fd","object":"chat.completion.chunk","created":1784770930,"model":"glm-5.2","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop"}],"service_tier":"default","first_token_return_time":1784770931.1887114}

data: {"id":"4dc9cd5407fa4fcf92e5d547984819fd","object":"chat.completion.chunk","created":1784770930,"model":"glm-5.2","choices":[],"usage":{"prompt_tokens":14,"total_tokens":23,"completion_tokens":9,"prompt_tokens_details":{"cached_tokens":0},"completion_tokens_details":{"reasoning_tokens":0}},"service_tier":"default","first_token_return_time":1784770931.188748}

data: [DONE]