Access 11 Chinese LLMs through a single OpenAI-compatible endpoint. Change one line of code, save 80-99% on API costs.
Get Free API Key →If you're already using the OpenAI SDK, you're 90% done. Just change the base_url and api_key — everything else works identically.
from openai import OpenAI
# Just change these 2 lines:
client = OpenAI(
base_url="https://eaf9553505eeb8f5-115-190-107-107.serveousercontent.com/v1",
api_key="your-api-key"
)
# Everything else stays the same!
response = client.chat.completions.create(
model="deepseek-v4", # or qwen3, glm-4, kimi-k3
messages=[{"role": "user", "content": "Hello!"}]
)
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://eaf9553505eeb8f5-115-190-107-107.serveousercontent.com/v1',
apiKey: 'your-api-key'
});
const response = await client.chat.completions.create({
model: 'deepseek-v4',
messages: [{ role: 'user', content: 'Hello!' }]
});
curl https://eaf9553505eeb8f5-115-190-107-107.serveousercontent.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-v4","messages":[{"role":"user","content":"Hello!"}]}'
| Model ID | Provider | Context | Best For |
|---|---|---|---|
| deepseek-v4 | DeepSeek | 128K | Latest flagship, general purpose |
| deepseek-r1 | DeepSeek | 128K | Reasoning, math, code |
| qwen3.6-flash | Alibaba | 32K | Fast responses, chatbots |
| qwen-max | Alibaba | 128K | High quality, content gen |
| glm-4-flash | Zhipu AI | 128K | Ultra-fast inference |
| kimi-k3 | Moonshot | 128K | Long documents, research |
| OpenAI GPT-4o | AI Token Hub (DeepSeek V4) | |
|---|---|---|
| Input cost / 1M tokens | $2.50 | $0.005 |
| Output cost / 1M tokens | $10.00 | $0.01 |
| API format | OpenAI | OpenAI-compatible ✅ |
| SDK changes needed | — | 2 lines |