Switch your client in three lines

Base URL and Authentication

Our API is fully OpenAI-compatible. To use it, update your client's base URL to https://api.uncensoredgpt.cc/v1 and provide your API key. You generate this key instantly on the Get API key page by signing in with Google or an email password. No phone number is required, and the key is shown immediately. There is no need to manage subscriptions or monthly fees; you simply top up credit and pay for what you use.

First Request

Send a standard chat completion request to POST /v1/chat/completions. The model ID is uncensored. This is a single open-weight model tuned for lawful adult use, not a routing aggregator. You can send text inputs and receive text outputs. If you need streaming, set stream: true. The model handles function calling and JSON mode natively. Errors and refusals are free; you only pay for tokens used.

Python SDK Integration

Use the official OpenAI Python library to integrate quickly. Set the environment variable or pass the key directly. The client will route requests to our endpoint automatically. This works for both sync and async calls. You can control parameters like temperature, top_p, and stop. The response includes token usage details. This approach keeps your code compatible with OpenAI while using our uncensored model.

Node SDK Integration

The Node.js SDK works identically. Configure the base URL and API key in the client initialization. Send messages as an array of role-based content. The API supports the same parameters as the OpenAI standard. You can parse the response to extract text or function calls. This is a reliable way to add an uncensored LLM to your Node applications without rewriting your logic.

Streaming Responses

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE). Each chunk contains partial text. The final chunk includes the total token usage for the request. This is useful for real-time UI updates. You can parse the stream to display tokens as they arrive. This reduces perceived latency for users waiting for long responses.

Limits, Errors, and Context

Your API key is limited to 300 requests per minute and 8 concurrent requests. The request body must be under 8 MB. The context window is 64,000 tokens total, with a max output of 16,000 tokens (2,048 if max_tokens is unset). You will receive a 401 if the key is invalid, a 402 if you have no credit, and a 429 if you exceed the rate limit. Credit never expires, so you can top up at your own pace.

cURL

Copycurl https://api.uncensoredgpt.cc/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."}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.uncensoredgpt.cc/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.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uncensoredgpt.cc/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)