NSFW LLM: Uncensored LLM API Quickstart

Base URL & Authentication

Our API follows the OpenAI standard, making integration straightforward. Use the base URL https://api.nsfwllms.com/v1 for all requests. Authentication is handled via a Bearer token in the Authorization header. You can generate your key on the Get API key page using just an email and password. No phone number or credit card is required to start with the free trial credit.

First Request

Send a standard chat completion request to test connectivity. The model identifier is uncensored. This request demonstrates the basic text-in, text-out flow without any special parameters.

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

This returns a standard response object containing the generated text. If you receive a 401, verify your API key. A 402 indicates your prepaid credit balance is insufficient.

Python SDK Integration

Use the official openai Python package to interact with the endpoint. Set the base URL to point to our servers and provide your API key. This allows you to leverage familiar SDK patterns for your uncensored LLM applications.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.nsfwllms.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 client handles serialization and retry logic automatically. You can pass model="uncensored" to ensure you are hitting the correct abliterated model.

Node SDK Usage

For JavaScript or TypeScript projects, initialize the OpenAI client with the custom base URL. This approach works with any OpenAI-compatible client library that supports custom endpoints.

Copyimport OpenAI from "openai";

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

Ensure you are using a recent version of the SDK that supports the baseUrl configuration. This ensures compatibility with our streaming and tool calling features.

Streaming Responses (SSE)

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) that you can process incrementally. This reduces perceived latency for chat interfaces.

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)

Each chunk contains partial text deltas. Concatenate these deltas to reconstruct the full response. Streaming works identically to the standard OpenAI protocol, so existing stream parsers should work without modification.

Rate Limits & Constraints

Each API key is limited to 300 requests per minute. The maximum request body size is 8 MB. The context window supports up to 100,000 tokens total for prompt and completion combined. If you exceed the rate limit, you will receive a 429 error. You can regenerate your API key at any time, which immediately revokes the previous key.