Developer quickstart for uncensored LLM

Base URL and Authentication

Start by pointing your client to our base URL. We host a single uncensored large language model at https://api.chatbotunfiltered.com/v1. This endpoint replaces the standard OpenAI address, ensuring your existing code works without modification. Generate an API key via the dashboard using Google or email, then set it in your headers. We do not offer embeddings or image generation, only text completion.

Chat Completions Endpoint

Send your first request to POST /v1/chat/completions. Use the model ID uncensored to access the unfiltered model. This endpoint accepts standard message arrays and returns generated text. You can verify connectivity by listing models via GET. Keep your payload under 8 MB to avoid truncation.

Copycurl https://api.chatbotunfiltered.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

Python SDK Integration

Configure the official Python SDK to target our base URL. Pass your API key as a header or environment variable. Set the model name to uncensored for consistent results. The SDK handles serialization automatically. Use this setup for quick scripts or complex role-play logic.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.chatbotunfiltered.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 Configuration

Initialize the Node client with our specific base URL. This ensures your JavaScript applications route requests correctly. The uncensored model ID remains constant across all SDKs. Configure the API key in your environment variables for secure access. This approach works seamlessly with Express or serverless functions.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.chatbotunfiltered.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 with SSE

Enable streaming by setting stream: true in your request. We return Server-Sent Events (SSE) for real-time token delivery. The final chunk includes the complete token usage statistics. This method reduces perceived latency for long conversations. Handle the stream events in your client-side code.

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)

Rate Limits and Concurrency

Expect a limit of 300 requests per minute per key. You can run up to 8 concurrent requests simultaneously. If you exceed these bounds, you receive a 429 status code. Authentication failures return 401, and insufficient credit returns 402. The context window supports 100,000 tokens total. Errors during generation do not consume your prepaid credit.