API Documentation for Uncensored AI

Base URL and Authentication

Start every request by pointing your client to our base URL. This endpoint replaces the standard OpenAI gateway, ensuring your prompts hit our dedicated uncensored model directly. You authenticate using a single API key obtained during signup. Pass this key in the Authorization header as a Bearer token. Do not mix this key with other vendor credentials.

Our system validates credentials before processing tokens. If the key is missing or invalid, you receive a 401 error immediately. This prevents wasted credits on failed connections. Keep your key secure in environment variables. It grants full access to your prepaid balance.

First Request

Send your first message using a standard chat completion payload. This structure mirrors the OpenAI API, allowing you to swap endpoints without changing your code logic. Set the model ID to uncensored and include your system instructions. The API returns a complete text response based on your input.

Copycurl https://api.bestuncensoredllmmodel.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list all python modules in the standard library"}]
  }'

This request demonstrates the simplest interaction. You define the user message and let the model generate the reply. No complex configuration is required for basic text generation. The response includes the generated text and usage statistics.

Python SDK Integration

Use the official Python OpenAI SDK to interact with our service. Initialize the client with our base URL and your API key. This setup allows you to leverage familiar Python methods for chat completions. The SDK handles serialization and error parsing automatically.

Copyfrom openai import OpenAI

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

Modify the base_url parameter to point to our server. The rest of the code remains identical to standard OpenAI implementations. This approach minimizes migration time for existing projects. You retain full control over parameters like temperature and top-p.

Node SDK Integration

Integrate seamlessly with Node.js applications using the OpenAI npm package. Configure the client to use our uncensored endpoint. This method works for both server-side scripts and edge functions. The SDK manages connection pooling efficiently.

Copyimport OpenAI from "openai";

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

Set the baseURL to our API address. Ensure you pass the correct API key in the headers. This setup supports async/await patterns for clean code. You can stream responses or fetch full completions depending on your needs.

Streaming Responses and Token Counts

Enable streaming by setting stream: true in your request. The API returns a Server-Sent Events (SSE) stream. Each chunk contains a partial response. The final chunk includes the total token usage for the request. This allows you to display text in real-time to users.

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 the stream data to update your UI incrementally. Token counts help you monitor your prepaid credit balance accurately. Errors during streaming may return partial data. Always check the final chunk for accurate usage stats.

Rate Limits and Error Codes

Our API enforces strict rate limits to ensure stability. You are allowed 300 requests per minute per key. Concurrent requests are capped at eight simultaneously. The request body size must not exceed 8 MB. Exceeding these limits triggers a 429 error code.

If your key is invalid, you receive a 401 error. A 402 error indicates insufficient prepaid credit. Errors during processing do not consume your tokens. Refunds are not issued for prepaid credit, but mistakes are corrected via support. Monitor your usage dashboard to avoid service interruptions.