GLM-4-Flash / 5.3

from openai import OpenAI

# 1. 替换为对应厂商领取的 API Key 与 Base URL (参见下方厂商雷达表)
client = OpenAI(
    api_key="your_api_key_here",
    base_url="https://api.siliconflow.cn/v1"  # 示例: 硅基流动直连端点
)

response = client.chat.completions.create(
    model="glm-4v-flash",
    messages=[
        {"role": "system", "content": "You are a helpful AI assistant."},
        {"role": "user", "content": "Hello! Please introduce yourself briefly."}
    ],
    temperature=0.6,
    stream=True
)

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

curl https://api.siliconflow.cn/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your_api_key_here" \
  -d '{
    "model": "glm-4v-flash",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "temperature": 0.7
  }'