Quickstart: Integrate Uncensored Text into Your NSFW Image App

Authentication & Base URL

To start using the API, you need an API key from the Get API key page. Authentication is handled via the standard Authorization header. The base URL for all requests is https://api.nsfwimage.cc/v1. You can use any OpenAI-compatible client by updating the base URL and providing your key. This setup ensures compatibility with existing tools used in NSFW image generation workflows.

Sending Requests to /v1/chat/completions

The core endpoint is POST /v1/chat/completions. Send your prompt context as a JSON object with the model field set to uncensored. This model is tuned to answer without content refusals for lawful adult use. The response returns generated text, which you can use as input for image generation tools or to extract metadata.

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

Ensure your requests include the necessary headers and follow the standard chat-completions format for seamless integration into your pipeline.

Configuring JSON Mode for Structured Output

For automated NSFW image pipelines, structured output is critical. Use the response_format parameter set to {"type": "json_object"} to enforce JSON responses. This ensures predictable data structures for tool logic and post-processing. JSON mode works alongside other parameters like temperature and top_p to control creativity and format adherence. This feature is essential for parsing prompts or metadata programmatically.

Copyfrom openai import OpenAI

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

By enforcing strict JSON output, you reduce the need for complex parsing logic in your NSFW image generation scripts.

Handling Streaming Responses (SSE)

For real-time applications, enable streaming by setting stream: true. The API returns Server-Sent Events (SSE), delivering tokens incrementally. The final chunk contains the token usage statistics for billing and monitoring. Streaming is ideal for user-facing interfaces where immediate feedback is needed during NSFW image prompt generation. It allows you to display progress without waiting for the full response.

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 events appropriately to update your UI or log token usage accurately.

Managing Token Limits & Context Window

The model supports a 64,000-token context window, combining prompt and completion. The maximum output per request is 16,000 tokens, or 2,048 if max_tokens is unset. This capacity is sufficient for complex NSFW image prompt engineering and metadata extraction. Monitor token usage to optimize costs, as billing is based on actual token consumption. Errors and refusals do not incur charges.

Error Handling & Token Usage

Common errors include 401 (invalid key), 402 (insufficient credit), and 429 (rate limit). The rate limit is 300 requests per minute per key. Handle these errors gracefully in your NSFW image pipeline to maintain reliability. Token usage is detailed in the final streaming chunk or response headers. Errors are free, so failed requests do not affect your prepaid credit. Use the Support page for refund issues or double charges.

Node.js

Copyimport OpenAI from "openai";

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