Is this an official OpenAI service?

No, we are an independent provider offering an OpenAI-compatible API interface. We serve our own uncensored model, not GPT-4 or other vendor models.

How does the prepaid credit system work?

You top up with crypto (USDT or USDC) and pay only for tokens used. Errors and refusals do not consume your credit, and unused funds never expire.

What is the context window size?

The model supports a 100,000 token context window for both input and output combined. There is no separate output cap: a response can use all the room left in the window.

Documentation - Quickstart & SDK Guide

Base URL & Authentication

Start by pointing your client to HTTPS://api.polskillm.com/v1. Generate a key on our dashboard using Google or email, then pass it in the Authorization header as a Bearer token. No phone number is required for signup, ensuring quick access to the uncensored model for your projects.

First Request

Send a POST request to /v1/chat/completions with the model id "uncensored". The API accepts standard parameters like temperature and top_p to control creativity. Below is a basic curl example to verify your connection and receive a text response.

curl https://api.polskillm.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Translate this log entry to English"}]
  }'

Verify the response structure matches the OpenAI format for seamless integration into your existing tools.

Python SDK Integration

Use the official OpenAI Python library by setting the base URL to our endpoint. This approach ensures compatibility with your current codebase while leveraging our uncensored AI capabilities. The SDK handles tokenization and request formatting automatically for you.

from openai import OpenAI

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

Import the library and configure the client with your API key to start generating content immediately.

Node.js Client Setup

Initialize the OpenAI npm package with the custom base URL and your secret key. This setup works with any Node.js application needing direct access to the unrestricted model. Configure the client instance to point to our servers for low-latency responses.

import OpenAI from "openai";

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

Call the chat.completions.create method to send your prompt and receive the model's output.

Streaming Responses

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) allowing you to process tokens as they generate. This reduces perceived latency for users interacting with the NSFW LLM or character AI alternatives in real-time.

stream = 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 delta objects in each chunk to assemble the final response or update a UI incrementally.

Rate Limits & Errors

You are limited to 300 requests per minute and 8 concurrent requests per key. If you exceed these, you will receive a 429 status code. Common errors include 401 for invalid keys and 402 when prepaid credit is exhausted. The context window supports 100,000 tokens total, with no separate output cap.

OpenAI Compatible API Documentation