Wu Xianzhi API Quick Start Guide

Base Endpoint and Authentication

Wu Xianzhi API is fully compatible with the OpenAI standard API. All requests go to https://api.wuxianzhiapi.com/v1. You need an API Key for auth, placed in the header Authorization: Bearer YOUR_API_KEY. Keys are generated upon registration and can be regenerated anytime. We use prepaid credit that never expires, billed pay as you go with no subscription fees.

Send your first request

You can verify API connectivity directly with curl. Send a POST request to /v1/chat/completions, specifying the model ID as uncensored. This model is an open-weight model that operates independently, optimized for legal adult content and controversial topics, and does not refuse to generate content.

Ensure the request body includes the messages array. A 401 error means auth failed; 402 means insufficient balance.

复制curl https://api.wuxianzhiapi.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 Example

Python developers can use the official openai library directly. Just set base_url to our server and provide your API Key. The model ID is fixed to uncensored. We support text generation only, no embeddings or multimodal capabilities. Ideal for backend integration handling structured data.

复制from openai import OpenAI

client = OpenAI(base_url="https://api.wuxianzhiapi.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.js SDK Integration

Node.js developers can also use the openai npm package. Configure baseURL and apiKey; the logic matches OpenAI. This uncensored LLM API supports function calling; define functions via tools and the model returns structured JSON for execution. Ideal for building unrestricted AI apps.

复制import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.wuxianzhiapi.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 (SSE)

To reduce time-to-first-token, set stream: true in your request. The API returns chunked responses via Server-Sent Events (SSE). Crucial for real-time chat or long text generation. Clients must listen to the data event and parse JSON chunks. Streaming does not change billing; it is still based on total input and output tokens.

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, Errors, and Context Window

Each API key is limited to 300 requests per minute, with a maximum request body size of 8 MB. The context window is 100,000 tokens (including prompts and responses). Error codes include: 401 for invalid key, 402 for insufficient balance, and 429 for rate limit exceeded. The model hard-blocks sexual content involving minors, while other legal adult content remains uncensored. You can retrieve the model list via GET /v1/models.