Uncensored LLM API for NSFW Chatbots

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

Copyfrom openai import OpenAI

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

Copyimport OpenAI from "openai";

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

Why Choose Our Uncensored API

Use the text model to draft scene outlines or revise supplied dialogue. Provide clearly adult fictional characters and explicit boundaries, then review the output. The endpoint supplies one model ID; it does not guarantee that every prompt will receive the desired answer.

Charges follow successful input and output token usage. Paid credit does not expire; trial credit has a separate validity period. Streaming lets the client receive text as events arrive, but it does not guarantee a particular response time.

OpenAI Compatible SDK Integration

Integration is straightforward because we use the standard OpenAI Chat Completions format. If you have existing code that uses the OpenAI Python, Node.js, or other SDKs, you likely need to change only two things: the base URL and your API key.

Our base URL is https://api.nsfwaiapi.com/v1. When you send a request, specify the model ID as 'uncensored'. This simplicity means you can integrate our API into your existing pipelines without rewriting your entire application logic. We support both standard responses and streaming responses, giving you flexibility in how you handle data in your frontend or backend.

Pay-As-You-Go Pricing

We believe in transparent, predictable costs without hidden fees. Our pricing is simple: $0.15 per 1 million input tokens and $0.50 per 1 million output tokens. There are no monthly subscription fees, no minimum commitments, and no expiration dates on your prepaid credits. If you buy $50 worth of credits, you get a 5% bonus; buy $100, and you get 10% bonus.

Eligible new accounts can request a $0.50 trial for 7 days; verification and processing may be required. Check the displayed balance before sending requests. Paid top-ups range from $20 to $500, with methods listed in checkout. Estimate usage from measured token counts.

Who This Is NOT For

The service generates text; it does not create images, audio or video, provide embeddings or fine-tuning, or select between vendor models. Check your requirements for deployment, data handling and any contractual SLA before choosing an integration.