OpenAI Compatible Interface Guide

Compatibility Principle

ChinaWHAPI's /v1/chat/completions endpoint accepts the exact same request format and fields as the OpenAI API, including messages, model, temperature, max_tokens, stream, etc.

SDK Integration

Simply change the baseURL to ChinaWHAPI's address and pass your API Key to use any OpenAI-compatible SDK to call Chinese models.

Python Example

from openai import OpenAI

client = OpenAI(
    api_key="{your_api_key}",
    base_url="https://chinawhapi.com/v1"
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "What is RAG"}]
)
print(response.choices[0].message.content)

Node.js Example

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "{your_api_key}",
  baseURL: "https://chinawhapi.com/v1",
});

const response = await client.chat.completions.create({
  model: "qwen3.6-plus",
  messages: [{ role: "user", content: "Write me a piece of code" }],
});

LangChain Integration

Use ChatOpenAI in LangChain and set openai_api_base to ChinaWHAPI's address.

Compatible Tools

Cursor, Jan, Cherry Studio, Postman, curl, Python openai package, Node.js openai package, LangChain, LlamaIndex, Dify, and all other tools that support custom base URL.

Notes

Some model parameters may not be supported by upstream (e.g., system_fingerprint for deepseek-r1). ChinaWHAPI will automatically filter incompatible parameters and return the actual upstream response.