from zai import ZaiClient

client = ZaiClient(api_key="YOUR_KEY")

response = client.chat.completions.create(
    model="glm-4.7",
    messages=[
        {"role": "system", "content": "You are helpful."},
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_ZAI_KEY",
    base_url="https://api.z.ai/api/paas/v4/"
)
# Use exactly like OpenAI SDK

response = client.chat.completions.create(
    model="glm-4.7",
    messages=[...],
    stream=True
)
for chunk in response:
    print(chunk.choices[0].delta.content, end="")

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get weather for a city",
        "parameters": {
            "type": "object",
            "properties": {
                "city": {"type": "string"}
            },
            "required": ["city"]
        }
    }
}]

response = client.chat.completions.create(
    model="glm-4.7",
    messages=[{"role": "user", "content": "Weather in Tokyo?"}],
    tools=tools,
    tool_choice="auto"
)

# Handle tool_calls in response.choices[0].message.tool_calls

response = client.chat.completions.create(
    model="glm-4.6v",
    messages=[{
        "role": "user",
        "content": [
            {"type": "image_url", "image_url": {"url": "https://..."}},
            {"type": "text", "text": "Describe this image"}
        ]
    }]
)

response = client.images.generate(
    model="glm-image",
    prompt="A serene mountain at sunset",
    size="1280x1280",
    quality="hd"
)
print(response.data[0].url)  # Expires in 30 days

# Submit
response = client.videos.generate(
    model="cogvideox-3",
    prompt="A cat playing with yarn",
    size="1920x1080",
    duration=5
)
task_id = response.id

# Poll for result
import time
while True:
    result = client.async_result.get(task_id)
    if result.task_status == "SUCCESS":
        print(result.video_result[0].url)
        break
    time.sleep(5)

response = client.chat.completions.create(
    model="glm-4.7",
    messages=[{"role": "user", "content": "Latest AI news?"}],
    tools=[{
        "type": "web_search",
        "web_search": {
            "enable": True,
            "search_result": True
        }
    }]
)
# Access response.web_search for sources

response = client.chat.completions.create(
    model="glm-4.7",
    messages=[...],
    thinking={"type": "enabled"},
    stream=True  # Recommended with thinking
)
# Access reasoning_content in response

if response.choices[0].finish_reason == "tool_calls":
    # Execute function and continue conversation
elif response.choices[0].finish_reason == "length":
    # Increase max_tokens or truncate
elif response.choices[0].finish_reason == "sensitive":
    # Content was filtered