GLM-4 Flash

curl -X POST https://api.tokencnn.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-4-flash",
    "messages": [{"role": "user", "content": "Summarize the key points of this document"}],
    "temperature": 0.7
  }'

import openai

client = openai.OpenAI(
    base_url="https://api.tokencnn.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="glm-4-flash",
    messages=[
        {"role": "user", "content": "Write a poem about AI in the style of Li Bai"}
    ],
    temperature=0.8,
    max_tokens=1024
)

print(response.choices[0].message.content)