Integrate Uncensored AI Chat in Minutes

Prerequisites and Base URL

To use the uncensored ai api, you need an API key and a basic understanding of how REST APIs work. Create an account via Google or email on the Get API key page. Your key is displayed immediately; there is no phone number required. The base URL for all requests is https://api.uncensoredaichat.top/v1. This endpoint is compatible with official OpenAI SDKs and any client that supports the OpenAI API specification. The only model available is uncensored, an open-weight model tuned for minimal content refusal in lawful adult contexts. It is not GPT, Claude, or any other vendor's model. You do not need to select a model version; simply reference uncensored in your requests.

Authentication and First Request

Pass your API key in the Authorization header as a Bearer token. The header format is Authorization: Bearer YOUR_API_KEY. This works for all endpoints. To verify your key and test the connection, send a simple chat completion request. If the key is invalid, you will receive a 401 error. If you have no credit, you will receive a 402 error. The following example demonstrates a basic text request using cURL.

Copycurl https://api.uncensoredaichat.top/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

This returns a text response. The uncensored model will answer directly without extra refusals for lawful adult topics. Note that the context window is 64,000 tokens total, with a max output of 16,000 tokens per request.

Python SDK Integration

Using the official OpenAI Python SDK is the fastest way to integrate. Install the package via pip, then initialize the client with your API key and the custom base URL. This approach handles retries and JSON parsing automatically. The model name remains uncensored. This method is ideal for backend services or scripts where you need synchronous responses. Ensure your base URL matches the API endpoint exactly. You can also set parameters like temperature and top_p to control response creativity.

Copyfrom openai import OpenAI

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

The response object contains the generated text in response.choices[0].message.content. Errors are raised as standard exceptions, allowing you to handle rate limits or billing issues gracefully.

Node.js SDK Integration

For JavaScript and TypeScript developers, the OpenAI Node SDK works seamlessly. Initialize the client with the base URL and your API key. This is useful for serverless functions, web servers, or Node-based applications. The API behaves identically to the Python version. You can send messages and receive text completions. The uncensored model responds to standard prompt structures. Use this SDK for building chat interfaces or integrating into larger Node.js ecosystems.

Copyimport OpenAI from "openai";

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

Access the response text via response.data.choices[0].message.content. Remember that the model is not a GPT variant; it is a distinct open-weight model optimized for unrestricted output. This ensures consistent behavior across different language wrappers.

Streaming Responses

For real-time user experiences, enable streaming by setting stream: true in your request. The API returns data via Server-Sent Events (SSE). Each chunk contains a portion of the text. The final chunk includes token usage statistics. This is essential for chat interfaces that display text as it is generated. Streaming reduces perceived latency for users. The uncensored model supports this feature fully. You can parse the SSE stream to append text to the UI incrementally.

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 end event to finalize the response. The token usage in the last chunk allows you to track costs accurately. Since billing is per token, streaming does not affect pricing; you pay for the total tokens generated.

Rate Limits, Errors, and Context Window

Each API key is limited to 300 requests per minute and 8 concurrent requests. The request body must not exceed 8 MB. If you exceed these limits, you will receive a 429 Too Many Requests error. Errors include 401 for invalid keys and 402 for insufficient credit. The context window is 64,000 tokens for prompt + completion combined. Max output is 16,000 tokens; if max_tokens is unset, it defaults to 2,048. Credit never expires, so you can use it whenever needed. No card is needed for the $0.50 trial.