NSFW API Quickstart Guide

Authentication and Base URL

Our API is OpenAI-compatible, so you can use existing SDKs with minimal changes. The base URL is https://api.nsfwapihub.com/v1. You must include your API key in the Authorization header as a Bearer token. Get your key from the dashboard after signing up with just an email. The key is shown immediately and can be regenerated anytime, which revokes the old one.

There is no phone number or card required for the trial. We use pay-as-you-go prepaid credits that never expire. New accounts receive $0.50 in trial credit valid for 7 days. For higher volume, top-ups start at $10, with bonus credits available at higher tiers. Keep your key secure; anyone with it can spend your credits.

First Request

Send a standard chat completion request to test your setup. Use the model ID uncensored to access our open-weight model tuned for adult content. The API accepts text input and returns text output. It does not support embeddings, images, or audio. Ensure your request body stays under 8 MB. This is a pure text completion API optimized for narrative and roleplay contexts.

The model answers without content refusals for lawful adult use, though sexual content involving minors is always blocked. You can use this endpoint for uncensored roleplay, creative writing, or any text-based application. The response includes the generated text and token usage statistics.

Copycurl https://api.nsfwapihub.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."}]
  }'

Python SDK Integration

Use the official OpenAI Python library to integrate quickly. Set the base_url and api_key in your client configuration. The rest of the syntax mirrors the standard OpenAI chat completions endpoint. This approach works for both synchronous and asynchronous applications. It is the most straightforward way to add an uncensored AI API to your Python backend.

Remember that the model ID is uncensored, not gpt-4 or similar. The API supports tool calling, so you can define functions in your system prompt or tools array. This allows for structured outputs or integration with external systems. The context window is 64,000 tokens, allowing for long conversations or large documents.

Copyfrom openai import OpenAI

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

Node SDK Integration

For JavaScript or TypeScript projects, the OpenAI Node SDK works directly. Configure the client with the base_url pointing to our API and provide your API key. This ensures compatibility with existing codebases that already use OpenAI-compatible services. You can switch between different providers easily by changing just these two configuration values.

The uncensored model handles standard chat messages. You can pass user and assistant messages to build a conversation history. The API returns completions that continue the narrative without unnecessary moralizing. This is ideal for character roleplay or adult-themed storytelling. Ensure you handle errors gracefully, especially rate limits and insufficient funds.

Copyimport OpenAI from "openai";

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

Streaming Responses

For a better user experience, use Server-Sent Events (SSE) to stream the response. This allows your application to display text as it is generated, reducing perceived latency. Set the stream parameter to true in your request. The API will return a stream of chunks, each containing a portion of the completion.

Process these chunks in your client-side code or backend proxy to build the final message. Streaming is supported by most OpenAI-compatible SDKs. This feature is essential for chat applications where users expect real-time interaction. The uncensored model generates text efficiently, making streaming a smooth experience for end-users.

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)

Rate Limits, Errors, and Context

You are limited to 300 requests per minute per API key. If you exceed this, you will receive a 429 Too Many Requests error. Requests are also limited to 8 MB in body size. If your key is invalid, you get a 401 Unauthorized error. If you run out of credits, you get a 402 Payment Required error. Refill your balance via the dashboard to continue using the service.

The context window is 64,000 tokens, including both the prompt and the completion. This allows for extensive conversation history or large input texts. The model is not GPT, Claude, or any other vendor's model; it is a distinct open-weight model. Ensure your application handles these limits and errors appropriately to maintain a smooth user experience.