What you get
Standard Endpoint
Use the familiar /v1/chat-completions structure with any OpenAI SDK. Change your base_url and API key to start generating text immediately.
Uncensored Output
Our model answers without refusing lawful adult, fictional, or controversial topics. It is tuned for unrestricted content generation.
Prepaid Transparency
Pay only for real tokens used. Errors and refusals do not charge your credit. Unused credit never expires.
Crypto Only
Top up with USDT (TRC20) or USDC (Base). No credit cards, PayPal, or bank transfers required for any transaction.
Large Context Window
Support up to 100,000 tokens for input and completion. Generate long responses with a max output of 32,000 tokens.
Developer Controls
Full support for streaming, function calling, JSON mode, and standard parameters like temperature and top_p.
How it works
Get Your Key
Sign up with Google or email and retrieve your API key instantly without phone verification.
Top Up Crypto
Deposit USDT or USDC to activate your prepaid credit balance.
Send Requests
Point your client to our base URL and start generating uncensored text.
What people build with it
- NSFW Content Generation
- Generate adult fiction or roleplay without hitting standard content filters. The model is tuned to accept lawful adult themes.
- Data Analysis
- Process large documents within the 100k context window. Use JSON mode to extract structured data from text reliably.
- Creative Writing
- Write stories or scripts without interruptions from moralizing refusals. Control the tone with temperature and seed parameters.
- Security Research
- Test LLM boundaries and jailbreaks with a model that does not over-refuse controversial or technical topics.
Direct OpenAI-Compatible Integration
We provide a single, high-performance uncensored model accessible via the standard OpenAI chat-completions endpoint. This means you can use your existing code with the official OpenAI SDKs or any compatible client. You only need to update your base_url to https://api.uncensoredgpt.top/v1 and set your API key. We do not aggregate models or offer complex routing. You get direct access to our open-weight model, tuned specifically for unrestricted output. This eliminates the overhead of enterprise platforms that bundle chat UIs or charge for multiple model types.
The API supports streaming via Server-Sent Events, function calling, and JSON mode. You retain full control over parameters like temperature, top_p, and stop sequences. If you need embeddings or image generation, this is not the right endpoint. We focus strictly on text-to-text generation for developers who want predictable, uncensored results.
Transparent Token Pricing
Our billing is based entirely on real token usage. You pay $0.25 per 1 million input tokens and $1.00 per 1 million output tokens. Errors and refusals do not consume your credit. This ensures you only pay for what you actually receive. There are no monthly subscriptions, no hidden fees, and no usage tiers that change your price. Your prepaid credit never expires, so you can top up when it suits you.
Unlike services that charge for prompt tokens even when they fail, we charge only for successful completions. This makes our uncensored gpt service cost-effective for high-volume testing and production workloads. You can track your usage and balance directly in your account dashboard. No surprises when the bill arrives because everything is prepaid.
Crypto Payments & Prepaid Credit
We accept crypto payments exclusively to keep the process simple and global. You can top up with USDT on the TRC20 network or USDC on the Base network. Minimum deposits start at $10, with a +5% bonus on $50 deposits and a +10% bonus on $100 deposits. We do not accept credit cards, PayPal, or bank transfers. This approach allows you to use the service without linking personal banking details.
New accounts receive $0.50 of trial credit valid for 7 days. No card is required to start. The trial is one per person and requires no phone number. Once your trial expires or credit runs out, you can top up with crypto at any time. Mistakes like double charges are handled via our Support page, and credits are not refunded but remain available for future use.
Uncensored Model Capabilities
Our model is an open-weight model run on our own servers. It is tuned to answer without content refusals for lawful adult use. It does not block controversial, fictional, or security-related topics. However, we enforce a hard limit: sexual content involving minors is always refused. This is the only strict content filter applied to every request.
The model supports a 100,000 token context window, allowing for long conversations or document processing. You can generate up to 32,000 tokens per request. If you do not set max_tokens, the default output limit is 2,048 tokens. We do not claim to match specific benchmark scores of other vendors, as our focus is on unrestricted output rather than leaderboard performance. Check the documentation for full parameter details.
Questions and answers
Is this an official OpenAI service?
No, we are an independent provider. Our API is compatible with the OpenAI format, but we run our own uncensored model. It is not GPT-4 or GPT-3.5, nor is it hosted by OpenAI.
What crypto networks do you accept?
We accept USDT on the TRC20 network and USDC on the Base network. We do not support other networks or payment methods like credit cards.
Does the model refuse adult content?
Generally, no. Our model is uncensored and allows lawful adult themes. The only hard limit is sexual content involving minors, which is always refused.
Can I use this for commercial projects?
Yes, you can use the API for any lawful purpose. There are no restrictions on commercial use, and your prompts are not used for training.
What happens if I overcharge?
If you experience a billing error like a double charge, contact us via the Support page. We will fix the issue. Your credit does not expire, so you can use it whenever you need it.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
