Uncensored LLM API quickstart

Install the standard OpenAI SDK

Start by adding the official library to your project environment. This ensures compatibility with our uncensored model without custom parsing logic.

• For Python: pip install openai
• For Node.js: npm install openai

These packages handle serialization automatically. You do not need third-party routing libraries or custom headers.

Configure base URL and API key

Point your client to our dedicated endpoint to bypass standard providers. Set the base URL to https://api.cheapestapikey.com/v1 and inject your key from the dashboard.

Authentication relies on a standard bearer token. Pass your unique key in the Authorization header or via the SDK configuration object.

Send your first uncensored chat completion

Make a request to the /v1/chat/completions endpoint with your desired prompt. The model accepts standard parameters like temperature and top_p.

Our uncensored model processes lawful adult, fictional, or controversial topics without refusal.

Copycurl https://api.cheapestapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list available endpoints"}]
  }'

Handle streaming responses and token usage

Enable streaming by setting stream: true to receive tokens in real-time. Each chunk contains partial text, and the final chunk includes the total token usage.

This approach reduces perceived latency for large outputs. You can process chunks as they arrive without waiting for the full 16,000 token limit.

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)

Use function calling and JSON mode

Structure your outputs for downstream applications using tools or strict JSON formats. Define functions in the tools parameter and let the model choose the best action.

Alternatively, enforce structured data with response_format: {"type": "json_object"}. This ensures consistent parsing for your NSFW chatbot or automation scripts.

Copyfrom openai import OpenAI

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

Check models and manage limits

Query GET /v1/models to verify available endpoints. Our system supports 100,000 tokens context and 300 requests per minute.

If you exceed limits, you will receive a 429 error. Ensure your key is active and funded, as errors like 401 indicate invalid credentials and 402 signals insufficient credit.

Copyimport OpenAI from "openai";

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