OpenAI SDK Compatibility
Use popular libraries like OpenAI Python or Node.js. Just change the base_url and API key to connect directly to our server.
Open-Weight LLM API
Uncensored LLM API for Zero Content Filters
Get access to a content-filter-free AI model suitable for security research, valid adult content, or unlimited creativity. The API is fully compatible with the OpenAI ecosystem for quick integration.
Try in one request
curl https://api.apitanpasensor.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.apitanpasensor.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.apitanpasensor.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);- Uncensored open-weight model
- 100,000 token context
- Transparent pay-as-you-go pricing
$0.25per 1M input tokens
$1.00Output tokens / 1M
100,000token context
$0.50free trial credit
300requests per minute
What you get
Streaming & Tool Calling
Server-Sent Events (SSE) support for fast responses and tool calling support for external function integration without changing the core code structure.
Guaranteed Data Privacy
Your prompts are not used to train the model. Only email and password are required for registration, with no phone verification.
100k Context Capacity
The model supports a 100,000 token context window, allowing processing of long documents or very detailed conversation history in a single request.
No Hidden Fees
Pay only for the tokens used with prepaid credit. No monthly subscription fees or confusing long-term commitments.
Full API Key Control
Regenerating an API key immediately revokes the old one. Each account is limited to one active key for tighter access security.
How it works
Create Account
Register with an email and password to get an API key and a $0.50 trial credit valid for 7 days.
Configure Client
Set base_url to https://api.apitanpasensor.com/v1 and enter the model id "uncensored" in your SDK configuration.
Send Request
Use the /v1/chat/completions endpoint to get direct text responses from the uncensored content model.
What people build with this API
Security Research
Analyze model responses to jailbreak prompts or controversial themes without automatic filters that often limit in-depth analysis.
Valid Adult Content
Generate narratives or stories with adult themes naturally without the risk of rejection by overly strict moderation systems.
Writing Assistant
Help authors generate more raw and authentic creative content, allowing for a wider variety of language styles.
Automated Integration
Use tool calling to connect AI with databases or external APIs to automate complex tasks.
Key Features of the Uncensored API
This API is designed specifically for developers who need freedom of expression from LLM models. Our open-weight models are fine-tuned to not reject topics considered sensitive by major vendors, as long as they are within legal limits and for legitimate adult use. This differs from GPT or Claude, which often filter responses to maintain brand image. We offer full transparency: you know exactly which model is running on our servers without unnecessary creativity restrictions.
One of the main advantages is streaming support via Server-Sent Events (SSE). This allows your application to display text results in real-time, significantly improving the user experience. Additionally, tool calling support allows you to add external capabilities like web search or calculation without significantly changing the core code architecture.
100k Token Context Capacity
A 100,000-token context window lets you pass long documents, extensive conversation history, or highly detailed prompts in a single request. This is especially useful for applications that require deep understanding of prior context without losing important information. With a wide context window, the model can process complex data more accurately than models with smaller token limits.
To leverage this feature, ensure your request structure is efficient. Although the capacity is large, note that costs are calculated based on the total tokens used (input and output). With 100k token capacity, you can perform long text analysis or provide highly specific instructions to the model without splitting requests into smaller parts that might lose contextual nuance.
OpenAI SDK Compatibility
We adopt the OpenAI interface standard, so you can use familiar SDK libraries like openai-python or openai-node. Just point base_url to https://api.apitanpasensor.com/v1 and enter your API key. The model ID you should use is "uncensored". This approach minimizes development time because you do not need to learn a new protocol from scratch.
The main advantage is ease of migration. If you previously used another OpenAI-compatible service, switching to our service requires only minor changes to the client configuration. Streaming and tool calling are supported natively, so you can use these advanced features without complex additional configuration. This is an ideal solution for developers who want to quickly integrate with their AI infrastructure.
Who It Is and Is Not Suitable For
This is suitable for you if: you are looking for a model that does not easily reject certain topics, requires large context capacity, and prioritizes price transparency without monthly subscription fees. This service is ideal for security researchers, adult content writers, or developers who want to test the limits of AI models.
It is not suitable for you if: you need a specific model like GPT-4 or Claude, require image or audio generation, or need an SLA (Service Level Agreement) with specific uptime guarantees. We are an independent service focused on text and content freedom, not a replacement for large model ecosystems that offer various types of media.
Questions and answers
Does the free trial credit last forever?
Free trial credit of $0.50 for new accounts is valid for 7 days after registration. If you do not use it within that period, the credit expires. For long-term use, you can top up prepaid credit that never expires.
What if I regenerate my API key?
When you regenerate your API key, the old key is immediately revoked and can no longer be used. However, the prepaid credit balance in your account remains safe and unaffected by this key change. You only need to update your client configuration with the new key.
Is my prompt data used to train the model?
No. Data privacy is our priority. Prompts you send via the API are not used to train the base model. Account registration only requires email and password, with no need for phone number or credit card verification to get started.
Are there any content restrictions that still apply?
Yes, although our model is uncensored, there is one content restriction that always applies: sexual content involving minors will still be blocked. For other valid adult topics, the model will respond without rejection.
How do I top up my credit balance?
You can top up your credit balance starting from $20 using a credit card or cryptocurrency. Additional bonus credit is available if you top up a certain amount: +5% bonus for a $50 top-up and +10% bonus for a $100 top-up. The balance you top up will never expire.
Getting your key takes just one step
Create an account, copy your key, change the base URL. That's it.
