Deployed overseas. Zero GFW issues. OpenAI-compatible interface. Access DeepSeek, Qwen, GLM, Kimi and more with a single API key.
Connect to China's leading AI model providers through one unified API
Detailed specifications and capabilities of every model available
Pay only for what you use. No monthly subscriptions. Up to 95% cheaper than OpenAI.
| Provider | Model | Input (Cache Hit) | Input (Cache Miss) | Output | Context |
|---|
* All prices in USD per 1M tokens. Automatic context caching applies to repeated prompt prefixes.
OpenAI-compatible interface. Switch in 2 lines of code.
pip install openaifrom openai import OpenAI
client = OpenAI(
api_key="tk-your-key-here",
base_url="https://your-domain.com/api/v1"
)
response = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)curl https://your-domain.com/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer tk-your-key-here" \
-d '{
"model": "deepseek-v4-flash",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'/api/v1/chat/completions
Chat completion (proxy)
/api/v1/models
List all models
/api/v1/providers
List providers
/api/v1/key/info
Check API key info