What is the NSFW LLM online API?

It is a hosted, OpenAI-compatible chat-completions API serving an uncensored large language model. It offers transparent prepaid billing with no monthly commitment and explicit crypto-only top-ups.

How does billing work?

You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals are free, and prepaid credit never expires. Top-ups are accepted via USDT (TRC20) or USDC (Base).

What are the context limits?

The model supports a 100,000 token context window for both prompt and completion. The maximum output per request is 16,000 tokens, or 2,048 if you do not set the max_tokens parameter.

Documentation - OpenAI Compatible API

Base URL and Authentication

The NSFW LLM online API operates on a single base URL: https://api.nsfwllmonline.com/v1. Authentication relies on a Bearer token passed via the Authorization header. You receive one active key per account, which you can regenerate immediately via the dashboard without losing your prepaid balance.

Base URL: https://api.nsfwllmonline.com/v1
Header: Authorization: Bearer YOUR_API_KEY

curl https://api.nsfwllmonline.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Return 200 ok json"}]
  }'

Chat Completions Endpoint

Use POST /v1/chat/completions to generate text. Send a model ID of uncensored to access our open-weight model tuned for unrestricted responses. The API accepts standard message structures, allowing you to build context-rich conversations or simple single-turn queries.

from openai import OpenAI

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

Supported Parameters

Control generation behavior with standard parameters like temperature, top_p, and stop. You can enforce JSON output using response_format or set a seed for reproducibility. The model supports a context window of 100,000 tokens, combining both input and output.

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.nsfwllmonline.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

Enable streaming by setting stream: true. The API returns Server-Sent Events (SSE) for real-time token delivery. Token usage metadata appears only in the final chunk, ensuring accurate billing tracking without blocking the response stream.

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)

Function Calling & JSON Mode

Use tool_choice and tools for function calling capabilities. For strict structured output, set response_format to {"type": "json_object"}. This ensures reliable parsing for automated pipelines without manual regex cleaning.

Rate Limits and Quotas

Each key allows 300 requests per minute and 8 concurrent requests. Requests exceeding 8 MB in body size are rejected. Common errors include 401 for invalid keys, 402 for insufficient prepaid credit, and 429 for rate limiting. The uncensored model refuses sexual content involving minors but allows other lawful adult topics.

API Documentation