NSFW AI API Documentation

Base URL and Authentication

Interact with the nsfw ai api using the standard OpenAI SDK format. Your base URL is https://api.nsfwaiapi.com/v1. Authentication is handled via a Bearer token in the Authorization header. Generate your key on the dashboard; it is displayed immediately after signup. No card or phone number is required for the initial trial.

Ensure your client library points to our base URL. The API serves a single uncensored model, so you do not need to select a model version for most requests. If you switch keys, the old one becomes invalid immediately.

First Request

Send a simple text completion to verify connectivity. The endpoint POST /v1/chat/completions accepts standard chat messages. Use the model ID uncensored to ensure you are routed to our open-weight model tuned for adult content.

This request demonstrates the core capability: text in, text out. The model will respond without standard content filters for lawful adult topics.

• Endpoint: POST /v1/chat/completions
• Model: uncensored
• Format: JSON

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."}]
  }'

If you receive a 401, check your API key. A 402 indicates your prepaid credit is exhausted.

Python SDK Integration

Use the official OpenAI Python library to integrate quickly. Set the base_url and api_key to match our service. This approach works for both synchronous and asynchronous workflows.

The model ID remains uncensored. Context window supports up to 100,000 tokens combined for prompt and completion. This allows for long-form roleplay or detailed analysis without cutting off early.

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)

This method is ideal for backend services that process text sequentially. Remember that prompts are not used for training, preserving your data privacy.

Node.js SDK Integration

For JavaScript or TypeScript projects, use the OpenAI Node.js SDK. Configure the client with our base URL and your API key. This enables seamless integration into web servers or Node.js scripts.

Ensure you handle errors appropriately, such as rate limits or insufficient credits. The API supports tool calling, allowing you to define functions the model can invoke.

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);

This setup is perfect for real-time chatbots or content generation pipelines. The pay-as-you-go model means you only pay for what you use, with no monthly fees.

Streaming Responses

For chatbots, streaming reduces perceived latency. Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) with incremental chunks.

This is critical for user experience in roleplay scenarios. The model generates tokens sequentially, sending them as they are ready.

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)

Handle the stream in your client to display text in real-time. This works with any OpenAI-compatible streaming parser.

Limits, Errors, and Quotas

Monitor your usage to avoid service interruption. The API enforces a limit of 300 requests per minute per key. The maximum request body size is 8 MB.

Common errors include 401 (invalid key), 402 (no credit), and 429 (rate limit). Credit never expires, so top up when convenient. Prepaid credits start at $10, with bonuses for larger amounts.

The context window is 100,000 tokens. Ensure your prompts fit within this limit. The uncensored model blocks sexual content involving minors, which is a hard limit.