glm-5.3-flash

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://your-domain.com/api/ai/v1"
)

response = client.chat.completions.create(
    model="glm-5.3-flash",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello, introduce yourself"}
    ]
)
print(response.choices[0].message.content)

stream = client.chat.completions.create(
    model="glm-5.3-flash",
    messages=[{"role": "user", "content": "Write a short poem about autumn"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

curl https://your-domain.com/api/ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3-flash",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": false
  }'