API Documentation

Authentication and Base URL

The API uses standard Bearer token authentication. You receive your key immediately after signing up with Google or an email address. Set the Authorization header to Bearer YOUR_API_KEY for all requests. The base URL is https://api.llmstatus.cc/v1. This endpoint works with any OpenAI SDK or compatible client. You only need to change the base URL and provide your key. No phone number is required for signup. Your identity stays minimal while you get full access.

First Request

Send a POST request to /v1/chat/completions to get an immediate response. The model identifier is uncensored. It handles adult content, security research, and controversial topics without refusal. You do not need a subscription or monthly fee. Errors do not consume your prepaid credit. Send your prompt and get text output directly.

Copycurl https://api.llmstatus.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Set the server timezone to UTC."}]
  }'

This request demonstrates the simplest possible interaction. The server returns a JSON object containing the generated text. You can adjust parameters like temperature or top_p to control creativity. The response includes usage statistics for transparency. Start with this basic call to verify your key works correctly.

Python SDK Integration

Use the official openai Python library to interact with the API. Configure the base URL and API key in the client initialization. The client handles serialization and error parsing for you. This approach reduces boilerplate code significantly. You can pass messages as a list of dictionaries. The model remains uncensored regardless of the client wrapper. Streaming and non-streaming modes are both supported. This method is ideal for backend services or data processing scripts.

Copyfrom openai import OpenAI

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

The SDK abstracts the HTTP details away. You focus on the prompt structure and response handling. Error codes are raised as exceptions. You can catch these to manage rate limits or credit issues gracefully. The code remains clean and readable. This is the recommended way for Python developers to integrate the API.

Node.js SDK Usage

Install the openai npm package for Node.js environments. Set the environment variable or pass the key directly to the constructor. The base URL must point to our service. This allows you to build serverless functions or web apps quickly. The SDK supports both CommonJS and ES modules. You can stream responses or get them in one go. The API key is passed securely in the header. This setup is perfect for JavaScript developers who need reliable text generation. No extra configuration is needed beyond the key and base URL.

Copyimport OpenAI from "openai";

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

The Node SDK mirrors the Python client structure. You send messages and receive completions. Error handling is built into the promise chain. This ensures your application stays robust. Use this method for real-time chat interfaces or background jobs. The code is concise and easy to maintain. You can extend it with custom headers if needed.

Streaming Responses

Enable streaming by setting stream: true in your request. The server sends Server-Sent Events (SSE) token by token. This reduces perceived latency for end-users. You receive partial responses as they are generated. The final chunk contains the total token usage. This is crucial for billing transparency. Streaming works with all parameters and tools. Use this mode for chat interfaces or live text generation. The client buffers tokens until the stream closes. This provides a smooth user experience without waiting for the full response.

Copystream = 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)

Handle SSE events in your code to update the UI in real time. The last event includes usage data. Parse this to track your credit consumption accurately. Streaming is optional but recommended for interactive apps. It keeps the connection open until completion. This method ensures you only pay for what is generated. Errors during streaming are reported in the final chunk.

Limits, Errors, and Context Window

You have a context window of 100,000 tokens for prompt and completion combined. Max output is 16,000 tokens per request. The limit is 300 requests per minute per key. You can have 8 concurrent requests at once. The request body cannot exceed 8 MB. A 401 error means your key is invalid. A 402 error indicates no credit is left. A 429 error signals you hit the rate limit. Credit never expires, so you can top up later. Errors do not charge your credit. Use these codes to debug your integration quickly. The API is strict but predictable. Plan your concurrency based on the 8-request limit.