NSFW llm API Documentation

Authentication & Keys

Sign in via Google or email to receive your single API key immediately. Use this key in the Authorization header for all requests. No phone number is required, and the key is shown instantly upon creation.

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

Copycurl https://api.llmnsfw.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Send a message as a shy librarian in a quiet archive"}]
  }'

Chat Completions Endpoint

Send a POST request to /v1/chat/completions with your prompt. The model ID is always uncensored. This endpoint returns text responses without the usual content filters for lawful adult topics.

Copyfrom openai import OpenAI

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

Parameters & Configuration

Control tone with temperature, top_p, and stop sequences. Use json_object mode for structured data. Set max_tokens to 16,000 for long outputs. The default output limit is 2,048 tokens if unspecified.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.llmnsfw.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 & JSON Mode

Enable streaming by setting stream: true. Token usage data appears in the final chunk. JSON mode ensures predictable parsing for your chatbot logic. Use tools for function calling capabilities.

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)

Error Handling & Limits

Handle 401 for invalid keys, 402 for insufficient credit, and 429 for rate limits. The limit is 300 requests per minute per key. Request bodies must stay under 8 MB. Errors and refusals are free.

Token Usage & Pricing

Pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. Top up with USDT or USDC. Credit never expires. The context window is 100,000 tokens.