Uncensored LLM API Docs

Base URL and Authentication

Use our dedicated base URL to connect your client. All requests require an API key passed in the Authorization header. This key is generated instantly upon signup via Google or email, ensuring no phone number is needed. The system enforces a single active key per account, replacing any previous key immediately.

Authentication is straightforward. Include Authorization: Bearer YOUR_API_KEY in every request. If the key is missing or invalid, the API returns a 401 error. This ensures your uncensored LLM access remains secure and tied to your prepaid credit.

Chat Completions Endpoint

Send text to POST /v1/chat/completions and receive direct text output. This endpoint serves the single uncensored model, eliminating guesswork about model routing or tier limits. You do not need to manage multiple endpoints for different capabilities.

Simply provide your messages in the standard format. The API processes the input and returns a completion. This approach keeps your integration simple while delivering high-quality, unfiltered content for roleplay or creative writing.

Copycurl https://api.generatoraiunfiltered.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list the top ten errors in this python script"}]
  }'

Python SDK Integration

Install the official OpenAI Python library and point it to our base URL. This allows you to use familiar methods like chat.completions.create() without rewriting your logic. The SDK handles JSON serialization and response parsing automatically.

Configure the client with your API key and the custom base URL. This setup lets you leverage existing code structures while accessing the uncensored model. It is the fastest way to integrate a reliable uncensored AI API into your Python projects.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.generatoraiunfiltered.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 Implementation

Use the openai npm package to connect your Node.js application. Set the baseURL and apiKey properties before making any calls. This ensures all requests route correctly to our uncensored model servers.

The Node SDK supports standard promise-based workflows. You can easily handle responses and errors within your existing asynchronous functions. This makes it ideal for server-side generation or background job processing.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.generatoraiunfiltered.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 and Tokens

Enable streaming by setting stream: true in your request. The API returns chunks as they are generated, allowing for real-time display. Token usage data is included in the final chunk, so you can track costs accurately.

Streaming reduces perceived latency for users. It is essential for chat interfaces or applications where immediate feedback matters. The unfiltered chatbot API handles streaming efficiently, ensuring smooth data flow without blocking your main thread.

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 Window

The model supports a 100,000 token context window for prompt and completion combined. Max output is 16,000 tokens per request. If max_tokens is unset, the limit defaults to 2,048 tokens. This allows for long-form content generation without frequent interruptions.

Rate limits are set to 300 requests per minute per key, with a concurrency limit of 8 simultaneous requests. Errors like 402 indicate insufficient prepaid credit, while 429 signals rate limiting. Request bodies must not exceed 8 MB. These constraints ensure stable performance for your unfiltered AI integration.