优速模式

curl -X POST https://{workspace_id}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.2-fast-preview",
    "messages": [{"role": "user", "content": "你是谁"}],
    "stream": false
}'

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ.get("API_KEY"),
    base_url=os.environ.get("BASE_URL"),
)

completion = client.chat.completions.create(
    model="glm-5.2-fast-preview",
    messages=[{"role": "user", "content": "你是谁"}],
    stream=True,
)

# glm-5.2 默认返回 reasoning_content 思考字段；
# 流式输出时思考内容与回答内容分别通过 delta.reasoning_content 与 delta.content 推送。
for chunk in completion:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    if hasattr(delta, "reasoning_content") and delta.reasoning_content:
        print(delta.reasoning_content, end="", flush=True)
    if hasattr(delta, "content") and delta.content:
        print(delta.content, end="", flush=True)

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "model": "glm-5.2-fast-preview",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "reasoning_content": "...",
      "content": "..."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 137,
    "total_tokens": 151,
    "prompt_tokens_details": { "cached_tokens": 0 },
    "completion_tokens_details": { "reasoning_tokens": 127 }
  }
}