Wu Shencha API Quick Start

Basic Configuration

The Wu Shencha API provides a standard OpenAI-compatible interface. You need to set the base URL and API key in your code. The base URL is fixed at https://api.wushenchaapi.com/v1. The model ID is uncensored, a fine-tuned open-weight model designed for uncensored scenarios, supporting lawful adult content.

The key is shown on the "Get API key" page after registration. Since the API is OpenAI-compatible, you can connect by simply modifying the base_url parameter in the official SDK. No extra routing or complex setup is needed.

Chat Completions Endpoint

Use the POST /v1/chat/completions endpoint to send text requests. The endpoint accepts standard message formats and returns generated text. This is the most basic interaction, suitable for most text generation scenarios.

The request body must include model, messages, and other fields. Ensure your request body size does not exceed 8 MB. If the key is invalid or the balance is insufficient, the API will return corresponding error codes.

复制curl https://api.wushenchaapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Python SDK

Python developers can use the official openai SDK. Point the base_url to the Wu Shencha API endpoint and pass your API key. This maintains consistency with native OpenAI code, making migration easy.

Ensure you have the latest SDK version installed. The code example shows how to initialize the client and send messages. This approach is concise and efficient, ideal for rapid prototyping.

复制from openai import OpenAI

client = OpenAI(base_url="https://api.wushenchaapi.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Node SDK

Node.js developers can also use the openai npm package. Configure it similarly to Python by setting baseURL and apiKey. This ensures cross-language consistency and reduces the learning curve.

Supports async requests and error handling. You can easily integrate it into existing Node.js applications. Handle async callbacks or Promises to avoid blocking.

复制import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.wushenchaapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Streaming

Supports streaming via Server-Sent Events (SSE). Set the stream: true parameter, and the API returns response data in chunks. This is useful for real-time apps or long text generation, providing a lower latency experience.

Streaming does not change model behavior, only the data transmission method. You can choose streaming or non-streaming mode as needed.

复制stream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Limits and Quotas

Up to 300 requests per minute. The context window is 100,000 tokens (including prompt and completion). The API returns a 429 error if limits are exceeded, 401 for invalid keys, and 402 for insufficient balance.

Prepaid credit never expires, with no monthly fees. Each request body is limited to 8 MB. These limits ensure service stability. You can generate a new key at any time to revoke the old one.