Integration guide: OpenAI-compatible endpoint

Base URL and authentication setup

Start by pointing your client to our endpoint. Use https://api.censureenon.com/v1 as your base URL. Pass your API key in the Authorization header. We provide one active key per account to keep things simple. Generate yours instantly after signing up with Google or email. No phone number required.

Copycurl https://api.censureenon.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list the top five npm packages for real time chat"}]
  }'

Making your first request

Send a standard chat completion payload to generate text. Our model id is uncensored. It handles adult content and unrestricted topics without refusal. Input goes in, text comes out. You can set a system prompt to define the persona. The API ignores standard content filters for lawful use.

Copyfrom openai import OpenAI

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

Streaming responses with SSE

Enable streaming by setting stream: true. You receive chunks of text in real-time. The final chunk contains the token usage data. This keeps memory usage low during long conversations. Use this for chat interfaces that need instant feedback. It works with any SSE-compatible client.

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)

Function calling and JSON mode

Use response_format with json_object for strict outputs. You can also define tools for function calling. Set tool_choice to force specific actions. This works with our uncensored AI models for structured data. Combine it with streaming for dynamic applications. Define your schemas clearly in the request.

Handling rate limits and errors

We enforce 300 requests per minute per key. You can run 8 concurrent requests. If you exceed the limit, you get a 429 error. A 401 error means your key is invalid. A 402 error indicates no credit. Errors and refusals do not consume tokens. Our context window is 100,000 tokens total. Manage your budget wisely.

Token usage and billing info

Pay only for what you use. Input tokens cost $0.15 per 1M tokens. Output tokens cost $0.50 per 1M tokens. Top up with USDT (TRC20) or USDC (Base). Minimum top-up is $20. Bonus credit applies at higher tiers. Credit never expires. No monthly fees lock you in. Start with a free trial.

Node.js

Copyimport OpenAI from "openai";

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