Uncensored AI Model For Coding: API Documentation

Base URL & Authentication

Our API follows the OpenAI chat-completions structure, allowing you to use existing SDKs with minimal configuration. The base URL is https://api.uncensoredcodingai.com/v1. Authentication is handled via a Bearer token in the Authorization header. You must include your API key exactly as provided during signup; there are no subscriptions or monthly fees, only pay-as-you-go prepaid credit.

Important: While the model is highly permissive, it does not remove all filters. A hard content limit always applies: requests containing sexual content involving minors will be blocked. All other lawful adult, controversial, or technical topics are processed without refusal.

First Request

Send a standard chat completion request to generate text. The model ID is uncensored. This is an uncensored coding llm optimized for code generation and technical tasks, not a clone of GPT or Claude. The model runs on our own GPU servers and is an open-weight model tuned for direct responses.

Copycurl https://api.uncensoredcodingai.com/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."}]
  }'

Replace YOUR_API_KEY with your actual key. The response will contain the generated text in the choices[0].message.content field. Ensure your input fits within the 100,000 token context window.

Python SDK Integration

Use the official openai Python package to interact with the API. Initialize the client with the custom base URL and your API key. This approach lets you leverage existing codebases that already support OpenAI-compatible endpoints.

Copyfrom openai import OpenAI

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

This script sends a prompt to the uncensored ai model and prints the response. The model ID is set to uncensored. You can adjust the temperature and max_tokens parameters to control creativity and output length. Remember that the uncensored llm does not have a memory of previous conversations unless you pass the full history in the messages array.

Node SDK Integration

For JavaScript and TypeScript projects, use the openai Node package. Configure the client with the baseUrl and apiKey environment variables or direct values.

Copyimport OpenAI from "openai";

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

This example creates a chat completion request using the uncensored model. The response object contains the generated text. You can handle errors and status codes directly within your Node.js application logic. This method is ideal for backend services or serverless functions that need to generate code or text on demand.

Streaming Responses

Enable streaming by setting stream: true in your request. The API returns a Server-Sent Events (SSE) stream, allowing you to display output as it is generated. This is useful for large code blocks or lengthy explanations.

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)

Process the stream chunks as they arrive. Each chunk contains partial text that you can append to your UI or log. Streaming reduces the perceived latency for the user, as they see progress immediately. The total response time still depends on the model's inference speed and the length of the output.

Limits, Errors & Context

Your API key is limited to 300 requests per minute. If you exceed this, you will receive a 429 Too Many Requests error. The request body size is capped at 8 MB. Authentication errors return a 401 status if the key is invalid. Billing errors return a 402 status if your prepaid credit is exhausted; top up from $10 to restore service.

The model supports a 100k context window (prompt + completion). Ensure your inputs fit within this limit. If you need more context, you may need to manage truncation in your application logic. The uncensored ai model for coding is designed for reliability, so monitor your usage to avoid interruptions.