Quickly integrate an uncensored large model API

Basic Configuration

Connecting to the API proxy core requires correctly configuring the Base URL and authentication credentials. Our service is fully compatible with the OpenAI protocol. You only need to set the Base URL to https://api.llmzhongzhuan.com/v1 and include your API key in the request headers.

Each account is assigned only one API key, which is displayed immediately upon registration. If you need to change it, you can regenerate it in the backend; the old key becomes invalid immediately. This design simplifies the authentication process and ensures access security. We do not support parallel management of multiple keys; we recommend managing keys reasonably according to your app architecture.

Generative Chat Interface

The standard chat interface is located at POST /v1/chat/completions. The request body must include the model (fixed to uncensored), the messages array, and optional parameters. This interface supports non-streaming responses, suitable for scenarios requiring complete return results.

The model runs on independently deployed high-performance GPU servers with a context window of up to 100,000 tokens. Whether processing long texts or following complex instructions, it provides a stable native API access experience.

复制curl https://api.llmzhongzhuan.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."}]
  }'

Streaming Response (SSE)

For apps requiring real-time feedback, enable the stream: true parameter to get chunked responses via Server-Sent Events (SSE). Streaming significantly reduces Time To First Token (TTFT), improving user experience.

The server continuously pushes JSON fragments until the response ends. The client must assemble these fragments to generate the complete text. This mode is ideal for chatbots or real-time content generation scenarios, ensuring data reaches end users quickly.

复制from openai import OpenAI

client = OpenAI(base_url="https://api.llmzhongzhuan.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)

Model List Query

You can get the list of currently available models via GET /v1/models. The request returns a standard JSON response containing fields like id, object, and owned_by.

Currently, there is only one model ID: uncensored. This is an open-weight model, specifically fine-tuned to remove content filters, suitable for adult content, safety research, and controversial topics. Note that we do not provide Embedding or multimodal generation services; we focus on pure text chat.

复制import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.llmzhongzhuan.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);

Error Handling and Rate Limiting

The service follows standard HTTP status codes. 401 Unauthorized means the API Key is invalid; 402 Payment Required means the account balance is insufficient and requires a top up before you can make further requests; 429 Too Many Requests means you have hit the rate limit, which is currently set to 300 requests per minute.

Additionally, the single request body size is limited to 8 MB. If you encounter rate limiting, we recommend implementing an exponential backoff retry strategy. Our uncensored AI service ensures fair resource allocation while maintaining high throughput.

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)

Example Code

Below is a complete example of making a streaming request using the Python SDK. The code shows how to initialize the client, build message history, and handle SSE data streams.

Make sure you have installed the openai library and replace YOUR_API_KEY with your actual key. This example intuitively shows how to get real-time generation results from the API proxy interface, making it easy for developers to integrate into existing systems.