NSFW Image API Quickstart

Authentication

Our API uses standard OpenAI-compatible authentication. You need an API key, which you can generate instantly on the Get API key page using Google or email. The key is displayed immediately after creation.

Include your key in the Authorization header for every request. Our base URL is https://api.nsfwimage.top/v1. This works with any OpenAI SDK or compatible client by updating the base URL and API key.

No phone number is required for signup. Your prompts are not used for training, ensuring privacy for your NSFW content workflows.

Basic Chat Completion

Send a simple text request to generate captions or style descriptions. The model ID is uncensored. It is an open-weight model tuned for lawful adult use without content refusals.

For example, you can ask for a detailed prompt for an NSFW image generation pipeline.

Copycurl https://api.nsfwimage.top/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."}]
  }'

Remember that the context window is 64,000 tokens total. If you do not set max_tokens, the output defaults to 2,048 tokens. Errors and refusals are free, so you only pay for successful token usage.

Python SDK

Use the official OpenAI Python SDK to integrate our uncensored LLM API into your pipeline. Set the base URL to our API endpoint and provide your key.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.nsfwimage.top/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 approach allows you to handle JSON responses and parse the generated text for your NSFW image metadata or prompt engineering tasks. The model handles style descriptions and post-processing text extraction efficiently.

Since we do not offer image generation, you will use this text output to guide your image or video generation tools. The pricing is transparent: $0.25 per 1M input tokens and $1.00 per 1M output tokens.

Node SDK

For JavaScript or TypeScript projects, use the OpenAI Node SDK. Configure the base URL to https://api.nsfwimage.top/v1 and inject your API key.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.nsfwimage.top/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 lets you integrate text generation directly into your web or server-side NSFW content pipelines. You can generate scripts, captions, or extract metadata from text sources.

Credit is prepaid and never expires. You can top up using crypto (USDT on TRC20 or USDC on Base) with amounts between $10 and $500. No card is needed for the trial credit of $0.50.

Streaming Responses

Enable streaming by setting stream: true in your request. This returns Server-Sent Events (SSE) for real-time token delivery, which is useful for large outputs.

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)

Token usage statistics are included in the last chunk of the stream. This feature works with all OpenAI-compatible clients. You can set temperature, top_p, and seed to control the randomness and reproducibility of your NSFW content generation.

Streaming helps reduce perceived latency when generating long prompts or detailed style descriptions for image pipelines.

Limits, Errors, and Context

Each API key is limited to 300 requests per minute and 8 concurrent requests. The maximum request body size is 8 MB. If you exceed these limits, you will receive a 429 error.

Common errors include 401 (invalid key) and 402 (insufficient credit). Errors are free, so you are not charged for failed requests. The context window is 64,000 tokens for input and output combined.

A hard content limit applies: sexual content involving minors is always refused. Otherwise, the model is uncensored for lawful adult use. No SLA or certifications are offered; this is a developer-focused API.