Quickstart: Integrating the Uncensored Chat API

Authentication & Base URL

Start by creating an account via Google or email. You will receive an API key immediately on the Get API key page. Use this key in the Authorization header for all requests. The base URL is https://api.nsfwvideogenerator.cc/v1. This URL is compatible with standard OpenAI SDKs; simply update the base URL configuration in your client.

• Header: Authorization: Bearer YOUR_API_KEY
• Base URL: https://api.nsfwvideogenerator.cc/v1
• Model ID: uncensored

No phone number is required for signup. The key is shown once, so store it securely. Errors and refusals do not consume credit, but valid requests are charged per token usage.

Chat Completions Endpoint

Send text to the POST /v1/chat/completions endpoint. The model ID is uncensored. This endpoint handles prompt engineering, script generation, and metadata extraction for your NSFW video generator pipeline. The model is uncensored, meaning it does not refuse lawful adult, fictional, or controversial topics. It does, however, block sexual content involving minors.

The context window is 64,000 tokens total. The maximum output per request is 16,000 tokens, or 2,048 if max_tokens is unset. You can control behavior using parameters like temperature, top_p, and stop. This is a text-only API; it does not generate video, audio, or images directly.

Python SDK Integration

Use the official OpenAI Python SDK to connect quickly. Configure the client with your base URL and API key. The following example demonstrates a basic chat completion request.

This setup works with any OpenAI-compatible client library. The response includes usage statistics and the generated text. You can use this text for captions, scripts, or metadata in your video pipeline. The model is open-weight and hosted on our servers, not a third-party vendor like GPT or Claude.

Ensure your SDK version supports the base URL override. The API key is validated server-side, returning a 401 error if invalid.

Node SDK Integration

For JavaScript environments, use the OpenAI Node SDK. Set the base URL to our endpoint and provide your API key. This allows you to integrate text generation directly into your backend services or serverless functions.

The Node SDK handles JSON parsing and streaming automatically. You can use the response text to drive downstream processes, such as generating scene descriptions or extracting metadata for your NSFW video generator platform. The API supports JSON mode via response_format for structured data output.

Remember that the model ID is always uncensored. You do not need to specify a version number; the API serves the current uncensored model.

Streaming Responses

Enable streaming by setting stream: true. The API returns Server-Sent Events (SSE) chunks. Each chunk contains partial text. The final chunk includes the token usage statistics, allowing you to track credit consumption accurately.

Streaming is ideal for real-time captioning or progressive script generation. It reduces perceived latency for your users. The server sends chunks until the response is complete or an error occurs. Errors during streaming do not consume credit.

Parse the SSE stream in your client code. Handle potential network interruptions gracefully. The context window applies to the entire conversation history, not just the current request.

Limits, Errors, and Context

Rate limits are 300 requests per minute and 8 concurrent requests per key. The maximum request body size is 8 MB. If you exceed these limits, you receive a 429 error. A 401 error indicates an invalid key. A 402 error means your prepaid credit is exhausted.

Credit is charged by real token usage. Errors are free. The maximum output is 16,000 tokens. The context window is 64,000 tokens. You can have only one active key per account; generating a new key replaces the old one.

Refunds are not issued for credit balance, but mistakes like double charges are fixed via Support. The trial credit of $0.50 is valid for 7 days.

cURL

Copycurl https://api.nsfwvideogenerator.cc/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."}]
  }'

Python

Copyfrom openai import OpenAI

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

Node.js

Copyimport OpenAI from "openai";

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

Streaming

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)