What is the base URL for the uncensored LLM API?

The base URL is HTTPS://api.providersapillm.com/v1. You can use any OpenAI-compatible client by pointing it to this URL and providing your API key.

How do I handle errors like 402 or 429?

A 402 error means you have no credit left, so you need to top up via crypto. A 429 error indicates you have exceeded the 300 requests per minute limit. Wait a moment or reduce your request frequency.

Is this API provider good for NSFW chatbot applications?

Yes, the model is uncensored and does not refuse lawful adult content. It is designed specifically for developers building NSFW chatbot apps or creative writing tools who need reliable text generation.

Documentation: Uncensored OpenAI-Compatible API

Base URL and Authentication

Use our base URL and an API key to connect any OpenAI-compatible client. The endpoint is https://api.providersapillm.com/v1 and your key grants access to the uncensored model. You get one active key per account, which you can replace if needed. The model ID to request is simply uncensored. This single model avoids complex routing and hidden filters found in multi-model gateways.

First Request

Send a standard chat completion request to generate text. The endpoint is POST /v1/chat/completions with the model ID set to uncensored. You can use the official OpenAI SDKs by changing the base URL. This works for NSFW chatbot apps and creative writing tools alike.

from openai import OpenAI

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

The model is open-weight and tuned to answer without refusals. It is not GPT, Claude, or any other vendor's model. Check the vendor documentation for their specific limits if you switch contexts.

SDK Integration

Integrate the API into your Node.js application using the standard SDK pattern. Set the base URL to our endpoint and use the model ID uncensored. This allows you to build reliable NSFW chatbot interfaces with minimal code changes.

import OpenAI from "openai";

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

The API supports standard parameters like temperature and top_p. You can adjust these to control the creativity of the output. Errors are returned in the standard format for easy debugging.

Streaming and Tools

Enable streaming via Server-Sent Events for real-time token generation. The final chunk includes token usage data for accurate billing. You can also use function calling and JSON mode for structured outputs. These features are essential for building advanced creative writing apps.

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)

Set response_format to {"type": "json_object"} for strict JSON responses. The model handles tools and tool_choice parameters effectively. This ensures your application receives predictable data structures.

Parameters and Limits

The context window is 100,000 tokens for prompt and completion combined. Max output is 16,000 tokens per request, or 2,048 if you do not set max_tokens. You are limited to 300 requests per minute and 8 concurrent requests per key. The request body must not exceed 8 MB.

You can use parameters like seed for deterministic outputs. The stop parameter allows you to define custom termination sequences. Adjust presence_penalty and frequency_penalty to refine the model's style.

Error Handling and Usage

Handle errors by checking the HTTP status code. A 401 indicates an invalid or missing API key. A 402 error means your prepaid credit is exhausted, and you need to top up. A 429 error signals that you have hit the rate limit of 300 requests per minute.

Credit is charged by real token usage. Errors and refusals are free. Prepaid credit never expires, so you can use it at your own pace. Support is available for issues like double charges.

cURL

curl https://api.providersapillm.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summarize the API documentation for authentication."}]
  }'

API Documentation