Build with DeepSeek, Qwen, GLM, Kimi, and MiniMax through a single OpenAI-compatible endpoint with unified billing and developer-friendly routing.
Point the OpenAI SDK or compatible client at https://api.xinoapi.com/v1. Existing chat-completions code stays in place while the selected model changes.
Start with DeepSeek for fast coding and reasoning loops, Qwen for balanced general-purpose work, then evaluate GLM, Kimi, or MiniMax against the task you actually ship.
Use one API key, one balance, and published model IDs instead of maintaining separate provider dashboards and SDK conventions.
XinoAPI is for developers and businesses outside mainland China. Plaintext prompts and responses are not retained by default; upstream provider terms still apply.
from openai import OpenAI
client = OpenAI(
api_key="xino-your-key-here",
base_url="https://api.xinoapi.com/v1",
)
response = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[{"role": "user", "content": "Hello from XinoAPI"}],
)
print(response.choices[0].message.content)Use explicit model IDs. Avoid legacy aliases in new integrations.
It is a unified API layer that routes requests to Chinese model providers while presenting an OpenAI-compatible interface.
XinoAPI is intended for developers and businesses outside mainland China.
XinoAPI focuses on DeepSeek, Qwen, GLM, Kimi, and MiniMax model families.
Review pricing, choose a model, and test with a small request before moving production traffic.