How to uncensor chat with our API

What is an uncensored chat model?

An uncensored chat model is a large language model that does not apply standard content filters to lawful adult, fictional, or controversial topics. Unlike models that refuse requests based on broad safety policies, our uncensored model is tuned to answer directly. It processes text in and outputs text out, providing an unfiltered chatbot experience for developers who need raw model behavior.

The model runs on our own servers as a single, open-weight model. It is not GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Llama, or any other vendor's model. We do not route between vendors. We host one uncensored model with a 100,000 token context window. This ensures consistent behavior without hidden filters interfering with your prompts.

Why standard APIs block your content

Standard APIs block content because they apply broad safety filters that reject lawful adult, fictional, or controversial topics. These filters often trigger on keywords or context, even when the content is perfectly fine for general audiences. You might ask a model to write a story, and it refuses because it detects a specific theme. This happens because the model is tuned for broad appeal, not precision.

Our API solves this by serving a model tuned to answer without content refusals for lawful adult use. The only hard limit that always applies is no sexual content involving minors. Requests of that kind are refused. Everything else is fair game. You get freedom from refusals and privacy by design, with no account overhead.

Step 1: Create your account and key

Create your account by clicking "Get API key" on our site. You can sign in with Google or use an email and password. No phone number is required. The API key is shown immediately after signup. A new key replaces the old one. You can top up your prepaid credit using crypto only. Acceptable coins are USDT on TRC20 or USDC on Base. Any whole amount from $20 to $500 is accepted. You receive +5% bonus credit from $50, +10% from $100, and +15% from $200. Paid credit never expires.

Step 2: Configure your OpenAI SDK

Configure your OpenAI SDK by changing the base URL and setting your API key. The base URL on this site is HTTPS://api.uncensorllm.com/v1. It works with the official OpenAI SDKs and any OpenAI-compatible client. You do not need to install new libraries. Just point your client to our endpoint.

• Base URL: HTTPS://api.uncensorllm.com/v1
• Model ID: "uncensored"
• Authentication: Bearer token with your API key

This setup ensures your requests are sent to our uncensored model. You can use the same code structure you already know. The only change is the destination. This makes integration fast and reliable for any developer.

Step 3: Send your first request

Send your first request by posting to the /v1/chat/completions endpoint. Use the model ID "uncensored" in your payload. The API accepts standard parameters like temperature, top_p, stop, seed, presence_penalty, and frequency_penalty. You can also use JSON mode with response_format json_object.

Function calling is supported via tools and tool_choice. Streaming is available via SSE, with token usage included in the last chunk. The context window is 100,000 tokens for prompt and completion together. Max output is 16,000 tokens per request, or 2,048 if max_tokens is not set. A request body cannot exceed 8 MB.

Handling streaming responses

Handle streaming responses by listening to Server-Sent Events (SSE) from the /v1/chat/completions endpoint. Each chunk contains partial text. The final chunk includes token usage details. This allows real-time display of generated text, improving user experience for chat interfaces.

Streaming works exactly like standard OpenAI streaming. You just need to parse the SSE format. The uncensored model responds to streaming requests without blocking. You can combine streaming with function calling for dynamic interactions. This feature is essential for building responsive chat applications.

Managing tokens and costs

Manage tokens and costs by paying per token usage. The price is $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals are free. You are charged only for real token usage. There is no subscription and no monthly fee. Prepaid credit is used for all charges.

Credit is topped up with crypto only. USDT on TRC20 or USDC on Base are accepted. Any whole amount from $20 to $500 is valid. Bonus credit is added automatically: +5% from $50, +10% from $100, and +15% from $200. Credit never expires. Mistakes like double charges are fixed through the Support page. Credit is not refunded.

Troubleshooting common errors

Troubleshoot common errors by checking your API key and request format. Ensure you are using the correct base URL: HTTPS://api.uncensorllm.com/v1. The model ID must be "uncensored". Requests exceeding 8 MB or 16,000 tokens (without max_tokens set) will fail.

You are limited to 300 requests per minute per key and 8 concurrent requests per key. If you hit these limits, wait or optimize your batch size. Errors do not consume credit. If you see unexpected refusals, check if the content involves sexual content with minors, which is always refused. Otherwise, the model should respond.

Final tips for reliable output

Get reliable output by using clear prompts and appropriate parameters. Set temperature for creativity or determinism. Use top_p for nucleus sampling. Define stop sequences to end generation cleanly. The uncensored model handles a wide range of topics without blocking lawful adult content.

Keep your prompts concise to stay within the 100,000 token context window. Remember, this is an API for developers, not a chat website. You control the interface. Use function calling for structured data. Stream responses for better UX. Your data is private, and prompts are not used for training. This setup gives you full control over your AI interactions.