API Documentation for Uncensored LLM

Authentication and Base URL

Connect by updating your base URL and providing your API key in the header. We host a direct, OpenAI-compatible endpoint that works with any standard client. You do not need to configure complex proxies or worry about model routing.

Set your authorization header to Bearer YOUR_API_KEY. The base URL for all requests is https://api.chatgptkartreddedildi.com/v1. Your key is generated immediately upon signup via Google or email. There is no phone number required, and your prompts are not used for training. This setup ensures you can switch to our uncensored model without changing your application code.

Chat Completions Endpoint

Send text prompts to POST /v1/chat/completions and receive text responses. This is the primary interaction point for our uncensored LLM. You can send messages with system instructions to guide the model's behavior. The model ID to specify is simply uncensored.

The API accepts standard chat formats. You can stream results or get full responses. Errors and refusals do not consume credit, so you only pay for successful token usage. The context window supports 100,000 tokens for both prompt and completion combined.

Copycurl https://api.chatgptkartreddedildi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the dependencies for this Python script"}]
  }'

Python SDK Integration

Use the official OpenAI Python library to integrate quickly. Point the client to our base URL and provide your API key. This approach lets you leverage existing libraries for message formatting and parameter handling. It is the most efficient way to test our API in a Python environment.

Configure the base URL to https://api.chatgptkartreddedildi.com/v1. Then call the chat completions endpoint with your desired messages. The library handles JSON serialization automatically. You can adjust parameters like temperature and top_p directly in the call.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.chatgptkartreddedildi.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 Integration

Integrate using the openai npm package with minimal configuration. Set the base URL and API key in the client options. This method allows you to use familiar Node.js patterns for asynchronous requests. It is ideal for web servers or backend services needing reliable text generation.

Instantiate the OpenAI client with your custom base URL. Pass your API key in the authorization header. Call the chat completions method with your message array. The response includes token usage and content. This setup ensures compatibility with standard OpenAI client code.

Copyimport OpenAI from "openai";

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

Enable streaming by setting stream: true in your request. You will receive a series of Server-Sent Events (SSE) chunks. Each chunk contains a small part of the generated text. This reduces perceived latency for end-users significantly.

The final chunk includes the full token usage statistics. You can accumulate the text parts to form the complete response. Streaming works with all parameters, including function calling. It is perfect for chat interfaces where instant feedback is critical. The API ensures that errors are handled gracefully without breaking the stream.

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)

Limits, Errors, and Context

Understand the rate limits and error codes for reliable integration. You are allowed 300 requests per minute per key. Only 8 requests can run simultaneously. The request body must not exceed 8 MB. If you exceed these limits, you will receive a 429 error. A 401 error indicates an invalid or missing API key. A 402 error means your prepaid credit is exhausted.

The context window is 100,000 tokens. This includes both the input prompt and the output completion. If you do not set max_tokens, the output is capped at 2,048 tokens. Errors and refusals are free, so you only pay for actual token usage. Credit never expires, and you can top up with crypto at any time.