One API Key for 38+
Chinese LLM Models

from openai import OpenAI

# Just change base_url — everything else stays the same!
client = OpenAI(
    api_key="your-aitoken-key",
    base_url="https://your-domain.com/v1"
)

# Call DeepSeek V4 (cheapest, best value)
response = client.chat.completions.create(
    model="deepseek-v4",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in 3 sentences."}
    ],
    temperature=0.7,
    max_tokens=500
)

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

curl https://your-domain.com/v1/chat/completions \
  -H "Authorization: Bearer your-aitoken-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    "temperature": 0.7
  }'

# Same client, same code — just swap the model name:

# Cheapest general-purpose model
response = client.chat.completions.create(model="deepseek-v4", ...)

# Best reasoning model (math, logic)
response = client.chat.completions.create(model="deepseek-r1", ...)

# Best for Chinese language tasks
response = client.chat.completions.create(model="qwen3.5-72b", ...)

# Best for long context (128K)
response = client.chat.completions.create(model="kimi-k2", ...)

# 34+ more models available with the same API key!