Uncensored AI App
Uncensored ai app API
Get reliable text generation from our uncensored AI app with a 100,000 token context window and no subscription locks.
- 100k token context window
- OpenAI-compatible endpoints
- Crypto prepaid credit
Test with a single call
curl https://api.uncensoredaiapp.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "List three ways to optimize postgres queries"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.uncensoredaiapp.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.uncensoredaiapp.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);Key benefits
OpenAI Compatibility
Use standard POST /v1/chat-completions with your existing OpenAI SDK clients.
Uncensored Model
Our open-weight model answers without refusals for lawful adult or creative content.
Streaming Support
Receive real-time token usage and data via Server-Sent Events (SSE).
JSON Mode
Enforce structured outputs with response_format json_object for reliable parsing.
Flexible Parameters
Control generation with temperature, top_p, stop sequences, and seed values.
No Expiration
Prepaid credits never expire so you can use them whenever you need.
Setup guide
Create Account
Sign up with Google or email to get your API key instantly.
Add Crypto Credit
Top up with USDT or USDC to start using the uncensored LLM.
Send Requests
Point your client to our base URL and start generating text.
Common use cases
Content Generation
Create unrestricted creative writing or roleplay scenarios without content filters.
Data Processing
Parse large documents using the 100,000 token context window efficiently.
API Integration
Integrate uncensored text capabilities into your existing applications or workflows.
Model Testing
Test model behavior with various parameters and streaming responses easily.
Cost examples: 100k tokens for $0.02
Costs depend entirely on your prompt and completion lengths. A 100k token input costs exactly $0.015. Adding 1k output tokens adds $0.0005. You pay only for real usage, not empty requests. Errors are free. Prepaid credit never expires. No subscriptions. No hidden fees. Transparent arithmetic. Pay less than a penny for typical small jobs. Use our prepaid credit system for exact budgeting. Crypto top-ups available.
Why developers choose our uncensored AI app
Developers select our uncensored AI app because it delivers consistent, refusal-free text generation for adult or controversial topics without subscription locks.
Transparent token arithmetic
We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors are free, so you only pay for usable text.
Crypto convenience
Top up with USDT or USDC. The "uncensored" model handles function calling and JSON mode reliably.
Avoiding common uncensored API traps
Developers often assume uncensored means unlimited output, but our model caps completion at 16,000 tokens per request. Another frequent error is ignoring streaming, which leaves clients hanging during long generations. Our API returns usage details in the final SSE chunk, preventing surprise charges from truncated responses. Always verify your client handles partial data correctly to avoid corrupted text files.
Switch from OpenAI in three steps
Switch instantly by updating your base URL and API key. First, generate your key via Google or email on our Get API key page. Second, set your base URL to HTTPS://api.uncensoredaiapp.com/v1. Third, point your SDK to model "uncensored". You now have access to an uncensored LLM for $0.15 per 1M input tokens. No subscriptions required, just pay-as-you-go crypto top-ups.
Who uses our uncensored API and who should skip it
Developers needing robust text generation for roleplay, creative writing, or adult content use our uncensored API. It handles unrestricted topics without artificial refusals. Skip it if you require image, audio, or video generation, as we provide text only. It is also unsuitable for teams needing multiple model routing or fine-tuning capabilities. Our service delivers a single, open-weight model via a standard interface, making it ideal for focused, uncensored LLM integration rather than broad multimodal suites.
Get your API key and make your first request
Setup your first request in 5 minutes
Start by creating an account using your Google login or a simple email address.
- Click “Get API key” to generate your unique credential instantly.
- Top up with crypto like USDT (TRC20) or USDC (Base) to add prepaid credit.
- Configure your OpenAI-compatible SDK with the base URL and your new key.
- Send a POST request to /v1/chat/completions with the model “uncensored” to receive your first text response.
Frequently asked questions
What is the uncensored AI app API?
It is a hosted OpenAI-compatible chat-completions API. It serves one uncensored large language model. Text in, text out. The model id is "uncensored". It is an open-weight model. It is not GPT, Claude, or any other vendor's model. No image or audio generation occurs.
Which payment methods do you accept?
Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.
Can I use the official OpenAI SDK?
Yes. The base URL is HTTPS://api.uncensoredaiapp.com/v1. It works with the official OpenAI SDKs. You must change the base_url. You must also set your API key. Any OpenAI-compatible client works. Streaming via SSE is supported. Function calling is available.
What are the context window limits?
The context window is 100,000 tokens. This covers prompt and completion together. Max output is 16,000 tokens. You can set 2,048 tokens if max_tokens is not set. Requests are limited to 300 per minute. Eight requests run simultaneously. The body maxes at 8 MB.
Is there a hard content limit?
Yes, a hard limit always applies. Sexual content involving minors is refused. Lawful adult content is allowed. Fictional topics are fine. Security research content is permitted. Controversial topics are not refused. The model answers without refusals. Illegal use is not encouraged. Minors remain protected.
How do refunds work?
Credit is not refunded. Mistakes are fixed via Support. A double charge is corrected there. Credit never expires. You keep your balance. Payments are crypto only. USDT and USDC are supported. Base and TRC20 networks work.
Get your API key now
Sign up, grab your key, and point to the new base URL. That’s it.
