Uncensored text API for your pipelineuncensored

Uncensored text API for your pipeline

Uncensored Text API for Stable Diffusion Pipelines

Power your Stable Diffusion pipelines with a reliable, uncensored LLM for prompt generation and post-processing. Get OpenAI-compatible text output without corporate safety filters.

Uncensored for lawful adult use
OpenAI-compatible SDK support
$0.50 free trial, no card needed

Get API key Read the docs

Try it in one request

curl https://api.sdxlapi.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."}]
  }'

from openai import OpenAI

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

import OpenAI from "openai";

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

$0.15per 1M input tokens

$0.50Output tokens / 1M

100,000token context

$0.50trial credit

300requests per minute

What you get

Uncensored Content

The 'uncensored' model answers without refusing lawful adult, fictional, or controversial topics. It is strictly text-focused, ensuring your creative vision isn't filtered by standard safety rails.

OpenAI Compatible

Works with official OpenAI SDKs and any compatible client by changing the base_url. Use your existing code to interact with our hosted chat-completions endpoint.

High Context Window

Supports 100,000 tokens for prompt and completion combined. Handle complex instructions, long scripts, or detailed metadata extraction in a single request.

Simple Pricing

Pay-as-you-go prepaid credit with no monthly fees. Rates are $0.15 per 1M input tokens and $0.50 per 1M output tokens.

Easy Integration

POST to /v1/chat/completions for streaming or tool calling. GET /v1/models to check availability. No complex setup required.

Secure & Private

Account creation requires only email and password. Prompts are not used for training. Regenerate your API key anytime to revoke access.

How it works

Create Account

Get Trial Credit

Receive $0.50 in trial credit valid for 7 days, no credit card required.

Integrate & Generate

Update your base_url in your SDK client and start generating uncensored text prompts.

What people build with it

Prompt Engineering

Generate detailed, uncensored image prompts for Stable Diffusion without content refusals. Customize tone and style for specific artistic niches.

Post-Processing

Extract metadata, captions, or tags from existing text or image descriptions. Refine generated text for consistency across your pipeline.

Script Writing

Create scripts for video workflows or voiceovers without content filters. Ideal for adult-themed or niche creative projects.

Data Extraction

Parse unstructured text into structured JSON for your application logic. Handle complex data formats with high context window support.

Why Text Matters in Your SD Pipeline

Most Stable Diffusion API guides focus on image generation, but the quality of your output depends heavily on the text input. Our uncensored LLM API handles the prompt generation and post-processing stages, ensuring your creative vision isn't filtered by standard corporate safety rails.

By offloading text tasks to a dedicated model, you get reliable, structured output for captions, metadata, or complex prompts. This keeps your image generation pipeline fast and focused, without waiting for a general-purpose model to decide if your prompt is 'safe' enough.

Uncensored Generation for Creative Freedom

Our model is tuned to answer without content refusals for lawful adult use. It does not apply standard safety filters to fictional, controversial, or niche topics. This means you can generate prompts for adult-themed art, dark fantasy, or specific cultural references without unexpected blocks.

Note that a hard content limit always applies: requests involving sexual content with minors are blocked. Everything else is fair game for creative freedom. This model is not GPT, Claude, or any other vendor's model; it is an open-weight model run on our own GPU servers.

OpenAI-Compatible SDK Integration

Use your existing code. Our API is hosted at https://api.sdxlapi.com/v1 and is fully compatible with the official OpenAI SDKs and any OpenAI-compatible client. Just change the base_url and provide your API key.

Support includes streaming via SSE and tool/function calling. The model ID to send is 'uncensored'. No embeddings, image, or audio generation here—just pure, high-speed text in and text out. This simplicity reduces integration time and keeps your stack lightweight.

Who This Is NOT For

If you need image, video, or audio generation directly from the API, this is not the right tool. We provide the intelligent text engine that powers the prompt engineering and post-processing stages of those pipelines, but we do not generate the media itself.

Similarly, if you require an SLA guarantee, SOC2 certification, or on-prem deployment, our service is not designed for those enterprise-grade requirements. We are a simple, pay-as-you-go text API for developers who value creative freedom and ease of use over rigid corporate guarantees.

Questions and answers

Is the API really uncensored?

Yes, the 'uncensored' model is tuned to answer without content refusals for lawful adult use. It does not filter fictional, controversial, or niche topics. However, requests of sexual content involving minors are always blocked.

How do I integrate with OpenAI SDKs?

Update your base_url to https://api.sdxlapi.com/v1 and set your API key. Use the model ID 'uncensored'. The endpoint is POST /v1/chat/completions, which supports streaming and tool calling.

What is the context window size?

The context window is 100,000 tokens, covering both prompt and completion. This allows you to handle complex instructions, long scripts, or detailed metadata extraction in a single request.

How does the pricing work?

We use a pay-as-you-go prepaid credit model with no monthly fees. Prices are $0.15 per 1M input tokens and $0.50 per 1M output tokens. Credit never expires.

Do I need a credit card for the trial?

No. Every new account gets $0.50 of trial credit valid for 7 days. You only need an email and password to sign up and get your API key immediately.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Get API key