Single Uncensored Model
We focus on one fine-tuned large language model optimized for adult content, controversial topics, and creative writing, ensuring requests aren't refused for sensitivity.
Stable & Uncensored
Uncensored LLM API: Connect in a few lines of code
Get unrestricted text generation via a single, powerful uncensored LLM API. Built for developers needing creative freedom and adult content without content filters.
- OpenAI Compatible Endpoint
- 100k Context Window
- Pay as you go, no monthly fee
Try it now
curl https://api.apidamoxing.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.apidamoxing.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.apidamoxing.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);- Input token price per 1M
- $0.25
- Output token / 1M
- $1.00
- Token Context
- 100,000
- Free Trial Credit
- $0.50
- Requests per Minute
- 300
Features
Streaming & Tool Calling
Supports streaming via SSE for low-latency responses and full tool/function calling, making it easy to integrate into complex apps.
100,000 Context Window
Supports a total context of 100,000 tokens per request (including prompt and output), allowing longer conversation history or document processing.
Transparent Pay as you go
Input tokens $0.25 per 1M, output tokens $1.00 per 1M. No monthly subscription, prepaid credit never expires, and top up gives extra credit.
Privacy First
Sign up with just email and password, no credit card needed. Your prompt data is not used to train the model, keeping your content private.
Quick Trial
New accounts get $0.50 free trial credit valid for 7 days. Start testing the API's performance and limits immediately without a credit card.
How it works
- 1
Get API key
Enter your email and password on the sign up page; your unique API key is displayed immediately.
- 2
Configure client
Set base_url to https://api.apidamoxing.com/v1 and enter your API key.
- 3
Send request
Send a POST request to /v1/chat/completions, specifying the model ID as uncensored to start generating.
Use cases
Adult content creation
For applications that need to generate uncensored roleplay or adult-oriented text, our model will not trigger content filters as frequently as general-purpose LLMs.
Free-style writing
Whether generating creative stories or technical docs, the model responds to your instructions rather than refusing based on preset moral standards.
Security research
Researchers can use the API for prompt injection or content boundary testing, as the model won't refuse specific requests within legal bounds.
Long-context applications
Build chatbots that remember long-term interaction history using a 100k context window, without frequent conversation truncation.
Why choose the uncensored API
Many general-purpose LLMs apply strict content filtering during generation, even for legal adult or controversial topics. The core value of the Da Moxing API is its single uncensored model. This is not multi-model routing; it focuses on one specialized fine-tuned open-weight model. It is optimized to accept adult content, fictional stories, and sensitive topics more readily within legal bounds.
This design eliminates the risk of unexpected rejections, making it ideal for applications with ambiguous content boundaries. You do not need to guess which model will accept your prompt, because our single model is built for this purpose. Prompt is content, you define the style, and the model executes the generation.
Core features: streaming and function calling
Our API is fully compatible with the OpenAI chat-completions endpoint. This means you can use any standard OpenAI SDK or compatible client by simply changing the base_url and API key. We support streaming via Server-Sent Events (SSE), which is critical for user interfaces that need to display generated text in real time.
Additionally, the API supports tool/function calling. You can define function structures, and the model will automatically select which function to call based on context and return structured data. This is useful for building intelligent assistants or automating workflows. Note that we provide text generation only; we do not offer image, audio, or video generation, nor embeddings or fine-tuning.
Simple and transparent pricing
We use a pure pay as you go model. The input token price is $0.25/1M, and the output token price is $1.00/1M. There are no hidden monthly subscription fees, and no rate limit tiers. Your prepaid credit never expires, and the more you top up, the more bonus you get (5% bonus for $50, 10% bonus for $100).
New users receive $0.50 in free trial credit upon registration, no credit card required, valid for 7 days. This allows you to fully test the model's performance and content acceptance. The rate limit is 300 requests per minute, with a maximum request body size of 8 MB, sufficient for the vast majority of API use cases.
Privacy and data security
Registering for the Da Moxing API requires only an email and password; no phone number or credit card information is needed. Our service operates independently and is not affiliated with any major cloud provider. Your prompt data is not used to train our models, ensuring your creative content remains private.
The only hard rule is that sexual content involving minors is always blocked. Otherwise, the model does not reject legal adult content. You can generate new API keys at any time, and old keys become invalid immediately, ensuring flexible key management.
Frequently asked questions
Is this API GPT or Claude?
No. We run an independent open-weight model, specifically fine-tuned for uncensored scenarios. It is not a model from OpenAI, Anthropic, Google, or any other provider.
What does uncensored mean?
This means the model will not reject legitimate adult content, controversial topics, or sensitive subjects. It is designed to generate content based on the prompt, rather than filtering based on preset content safety policies. The only exception is sexual content involving minors, which is always blocked.
Do I need a credit card for the free trial credit?
No. New accounts receive $0.50 in free trial credit upon registration, no credit card required. The trial period lasts 7 days and expires automatically afterward.
Who is this API for?
It is for developers who need to generate unrestricted text content, especially for adult content applications, creative writing, or scenarios requiring avoidance of content filtering. If you need image generation, embedding vectors, or multi-model routing, this is not the right choice.
What is the request rate limit?
Each API key is limited to 300 requests per minute, with a maximum request body size of 8 MB. This is sufficient to support most real-time applications and high-frequency call scenarios.
Just fill out the form to get your key
Create an account, copy the key, and modify the Base URL. Configuration is that simple.
