Uncensored LLM API
Apertus ia: The Uncensored LLM API
Access our uncensored ia model via a single OpenAI-compatible endpoint, delivering 100,000 token context windows for reliable, unrestricted text generation without monthly fees.
- OpenAI-compatible chat-completions API
- $0.15 per 1M input tokens
- Crypto-only prepaid billing
- $0.15
- per 1M input tokens
- $0.50
- Output tokens / 1M
- 100,000
- token context
- $0.50
- trial credit
- 300
- requests per minute
No subscriptions. Prepaid credits do not expire after 7 days.
Test with one call
curl https://api.apertusia.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "List the top 5 python libraries for web scraping"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.apertusia.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.apertusia.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);Core capabilities
Uncensored Model
Get unrestricted text generation without content refusals for lawful adult use.
Large Context
Process 100,000 tokens total, with output able to use all the room left per request.
OpenAI Compatible
Use official SDKs by simply changing the base_url and API key.
Streaming Support
Receive real-time responses via SSE with token usage details in the final chunk.
JSON Mode
Enforce structured output with response_format json_object for reliable data parsing.
Privacy First
No training on prompts, no phone number, and email-only account creation.
Setup process
Create Account
Sign in with Google or email to get your key instantly.
Top Up
Add crypto credits via USDT or USDC with instant bonus rewards.
Start Coding
Point your OpenAI SDK to our base_url and send requests.
Community projects
NSFW Chatbots
Build unrestricted conversational agents that handle adult content without arbitrary bans.
Research Analysis
Analyze sensitive data or controversial topics without model-specific content filters.
Content Generation
Produce long-form fiction or creative writing with full creative freedom.
Developer Testing
Test prompt responses in diverse contexts without unexpected refusal errors.
1. What Makes Apertusia Different: Open-Weight & Uncensored
Apertusia provides true uncensored text generation without arbitrary platform filters. Unlike typical providers that block lawful adult or controversial topics, our single open-weight model answers freely. We use transparent prepaid token billing with no monthly fees. You pay only for what you consume, ensuring privacy and simplicity for developers who need reliable, unrestricted LLM access.
| Feature | Typical Alternative | Apertusia |
|---|---|---|
| Content Filters | Strict, often opaque blocks | Uncensored, lawful adult content |
| Billing | Monthly subscription fees | Pay per token prepaid |
| Model Type | Proprietary black box | Open-weight, transparent |
| Privacy | Data used for training | Prompts not used for training |
2. From Signup to First Token: The 4-Step Workflow
Get your API key instantly and start generating uncensored text in under two minutes.
- Sign up via Google or email; no phone number required.
- The system displays your unique API key immediately for copy-paste.
- Configure your OpenAI-compatible SDK with the base URL and key.
- Send your first prompt to receive unrestricted responses.
This direct workflow ensures you begin testing the uncensored model without administrative delays or payment friction.
3. apertus ia: Real-World Use Cases for Uncensored Text
Our uncensored ia powers content pipelines needing raw, unfiltered generation.
NSFW Chatbot Development
Build adult-themed characters without arbitrary platform bans blocking your app.
Content Research
Analyze controversial topics with a model that does not refuse lawful, mature subjects.
Local Fine-Tuning
Use our API to generate training data from the open-weight Apertus model for your own private datasets.
4. Common Developer Questions About Our Model
Is Apertus ia open-source?
It is open-weight, meaning we provide the model weights for local use, but this API serves a hosted version on our servers.
Does it handle NSFW content?
Yes, the uncensored ia model answers without refusals for lawful adult topics, with the hard limit that minor sexual content is always blocked.
Is it just a wrapper?
No, we run the tuned model on our own infrastructure, ensuring direct control over latency and content filtering logic without third-party dependencies.
5. Migrate Your OpenAI-Compatible App in 3 Steps
Switching to our uncensored ia takes minutes because we mirror the OpenAI standard.
- Update your base URL to HTTPS://api.apertusia.com/v1 in your SDK configuration.
- Swap your API key from the old provider to the one generated here.
- Set model_id to "uncensored" to disable refusals.
This single change removes content filters while keeping your existing code intact.
6. Real Cost Examples: Token Math for Your Project
6. Real Cost Examples: Token Math for Your Project
- A 50k-token prompt costs $0.0075. We charge strictly for actual tokens used in each request.
- Generating a 10k-token response runs $0.005. Errors and refusals incur zero cost.
- Your total bill for this exchange is $0.0125. Prepaid credit covers usage without monthly fees.
Common queries
What is apertus ia and how does it differ from standard LLMs?
Apertus ia is an uncensored, open-weight model hosted on our servers. Unlike standard LLMs, it answers without content refusals for lawful adult use. We serve one model via a single API key, ensuring consistent behavior without routing complexity or hidden filters.
Does the uncensored model refuse any content?
Yes, one hard limit always applies: we refuse requests involving sexual content with minors. All other lawful adult, fictional, or controversial topics are processed normally. This single guardrail ensures compliance while maintaining the open, unrestricted nature of the model for developers.
Is the uncensored model open-source or open-weight?
It is an open-weight model run on our own servers. We do not claim it is fully open-source. You access it via our API endpoints, ensuring you get the tuned uncensored behavior without needing to manage local inference infrastructure or dependencies yourself.
How much does the uncensored LLM API cost per token?
Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. You pay only for real usage; errors and refusals are free. Credit never expires, and there are no monthly fees, making it predictable for high-volume NSFW chatbot deployments.
Can I use the standard OpenAI SDKs with this API?
Yes, the API is fully OpenAI-compatible. You simply change the base URL to our endpoint and provide your API key. This allows you to integrate seamlessly into existing applications without rewriting your code, supporting streaming, tools, and JSON mode responses.
What payment methods are accepted for topping up credit?
We accept only crypto: USDT on TRC20 or USDC on Base. Top-ups range from $20 to $500, with bonus credit added at higher tiers.
Secure your key now
Register, grab the key, point to our endpoint. Done.
