Quickstart: Integrate Our Uncensored LLM

Supported SDKs and Base URL Configuration

Our API works with any client that supports the OpenAI chat-completions protocol. You only need to update the base URL and provide your API key. The base URL for this service is HTTPS://api.aichatbotunfiltered.com/v1. This ensures compatibility with libraries like OpenAI’s Python SDK, Node.js SDK, and others.

Authentication relies on a single API key tied to your account. You generate this key during signup via Google or email. Each account holds one active key; generating a new one replaces the previous key immediately. Keep this key secure, as it controls your prepaid credit usage.

Sending Requests to the /v1/chat/completions Endpoint

Send your first request using the POST /v1/chat/completions endpoint. The model identifier is always "uncensored". This model responds to lawful adult content, roleplay, and creative writing without the typical safety filters found in other models.

Below is a basic curl example to verify connectivity. Replace YOUR_API_KEY with your actual key.

• Set the model to "uncensored".
• Provide a simple system and user message.
• Expect a direct text response.

Copycurl https://api.aichatbotunfiltered.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the steps to deploy a docker container."}]
  }'

Configuring Temperature, Top P, and Stop Sequences

Control the randomness and structure of the output using standard parameters. Set temperature between 0 and 2 to adjust creativity. Higher values produce more varied responses, which is useful for creative roleplay. Lower values yield more deterministic and consistent answers.

Use top_p to control the nucleus sampling. Set stop sequences to terminate the response at specific markers, such as dialogue boundaries. These parameters help tailor the model’s behavior to your specific use case without external routing.

Enabling Streaming and Function Calling

Enable streaming by setting stream to true. This returns tokens via Server-Sent Events (SSE). Token usage details appear in the final chunk, allowing you to track costs in real-time. Streaming reduces perceived latency for end-users.

You can also use function calling. Define tools in the request body to allow the model to output structured data or trigger actions. This works seamlessly with the standard OpenAI tool format. Use tool_choice to force specific behavior.

Copyfrom openai import OpenAI

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

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.aichatbotunfiltered.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

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)