Uncensored AI Chat Completions API

Base URL and Authentication

Your uncensored LLM API key grants access to the chat-completions endpoint. Use HTTPS://api.chatbotaiuncensored.com/v1 as your base URL. Pass your API key in the Authorization header as a bearer token. The key is shown immediately after signup. No monthly fees apply. Pay only for tokens used.

Chat Completions Endpoint

Send your first request to POST /v1/chat/completionsuncensored. The API accepts standard message arrays. It returns text responses. Errors are free. Refusals are free. You only pay for successful completions.

Copycurl https://api.chatbotaiuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list the top 5 python libraries for web scraping"}]
  }'

Python SDK Integration

Install the official OpenAI package. Set the base URL and API key. Call chat.completions.create with your prompt. The uncensored AI API returns text directly. You can adjust parameters like temperature or top_p. The response object contains the generated content. Use this for roleplay scripts.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.chatbotaiuncensored.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 Usage

Import the OpenAI client. Configure the base URL to point to our uncensored AI API endpoint. Set the API key in the headers. Call the completion method. The node SDK handles the request. You receive a stream or a direct response. This works for web apps. It works for backend services.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.chatbotaiuncensored.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 and Function Calling

Enable streaming by setting stream: true. You receive chunks as they generate. The last chunk includes usage data. You can also use function calling. Define tools in the request. The model returns tool calls. Parse these in your code. This enables complex workflows. Keep your app responsive.

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

You get 300 requests per minute. Eight requests run simultaneously. The context window holds 100,000 tokens. Errors return standard HTTP codes. A 401 means your key is invalid. A 402 means you need credit. A 429 means you hit the rate limit. Use these to manage your uncensored LLM API usage effectively.