NSFW LLM API Quickstart

Authentication and Base URL

Our API uses standard OpenAI authentication. Use the base URL https://api.nsfwllmapi.com/v1 and set your API key in the Authorization header. Sign up on the Get API key page to receive your key immediately. You can regenerate your key at any time; the old key is revoked immediately, though the rate limit counter continues from where it left off. Each account supports one key, and no card is needed for the trial.

Basic Chat Completion

Send a standard chat completion request to test the uncensored model. The model ID is always uncensored. This endpoint supports up to 64,000 tokens for the combined prompt and completion. Use this for simple text generation or roleplay setups where you need consistent content tolerance without routing complexity.

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

Ensure your system prompts allow adult themes if needed, as the model is tuned to answer without refusals for lawful adult content.

Python SDK Integration

Use the official OpenAI Python SDK to interact with the NSFW LLM API. Point the client to our base URL and pass your API key. This approach works well for backend services or scripts where you need structured responses. The SDK handles JSON serialization automatically, making it easy to integrate into existing Python pipelines.

Copyfrom openai import OpenAI

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

Remember that the model does not support embeddings or image generation, so keep your payload focused on text completion tasks.

Node SDK Integration

For JavaScript or TypeScript projects, the OpenAI Node SDK works seamlessly with our API. Configure the base URL and API key in your client instance. This is ideal for web-based chatbots or serverless functions that need to generate uncensored text responses. The SDK supports both synchronous and asynchronous patterns.

Copyimport OpenAI from "openai";

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

Handle errors gracefully, especially rate limits and credit exhaustion, to maintain a smooth user experience in your application.

Streaming Responses

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) for real-time token delivery. This reduces perceived latency for chatbot users, providing immediate feedback as tokens are generated. Streaming is supported for all standard chat completions and works with the OpenAI SDKs.

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)

Parse the SSE stream on the client side to display tokens as they arrive. This is critical for maintaining engagement in conversational interfaces.

Limits, Errors, and Context

The API enforces a limit of 300 requests per minute per key. If you exceed this, you receive a 429 error. Ensure your account has sufficient prepaid credit; a 402 error indicates no credit is available. An 401 error means the API key is invalid or revoked. The context window is 64,000 tokens. Requests exceeding 8 MB in body size will be rejected. Use these limits to design your retry logic and token management strategies effectively.