How to Use the Unfiltered AI API

Why Use an Uncensored API

Standard large language models often apply safety filters that refuse content which is perfectly lawful but considered mature or controversial. An uncensored AI API serves a model tuned to answer these topics without refusal, making it ideal for creative writing, roleplay, and adult-oriented applications. The model does not refuse adult, fictional, security-research, or controversial topics. It is not GPT, Claude, Gemini, or any other vendor's model; it is an open-weight model run on our own servers.

There is one hard content limit that always applies: sexual content involving minors is refused. Requests of this kind are blocked regardless of the prompt. For all other lawful adult content, the model provides direct, unfiltered responses. This makes the uncensored LLM API a reliable endpoint when you need text generation without the friction of safety refusals.

Understanding Token Costs

The pricing model is based strictly on raw token economics. You pay only for what you use, with prepaid credit that never expires. There are no subscription fees or monthly overheads. The rates are $0.25 per 1M input tokens and $1.00 per 1M output tokens. Errors and refusals are free, so you do not pay for wasted requests.

Credit is topped up using crypto only: USDT (TRC20) or USDC (Base). Any whole amount from $10 to $500 is accepted. There are bonuses: +5% credit for $50+ and +10% for $100+. You do not pay with a credit card, PayPal, or bank transfer. Mistakes like double charges are fixed through the Support page, and credit is not refunded but remains available since it never expires.

Integrating with OpenAI SDKs

The API is OpenAI-compatible, meaning you can use the official OpenAI SDKs and any OpenAI-compatible client. You only need to change the base URL and provide your API key. The base URL is https://api.unfilteredaichat.top/v1. The model ID to send is "uncensored". This is a chat-completions API; it does not offer embeddings, images, audio, or video generation.

• Endpoints: POST /v1/chat/completions and GET /v1/models.
• Context window: 64,000 tokens total (prompt + completion).
• Max output: 16,000 tokens per request, or 2,048 if max_tokens is not set.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.unfilteredaichat.top/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)

Streaming Responses

Streaming is supported via Server-Sent Events (SSE). This allows you to receive tokens as they are generated, reducing perceived latency for users. The final chunk of the stream contains the total token usage information. This is useful for applications that display text in real-time.

Parameters like temperature, top_p, stop, seed, presence_penalty, and frequency_penalty are supported. Streaming does not change the token cost; you still pay for the total input and output tokens used. The uncensored API handles streaming efficiently, ensuring a smooth data flow for your application.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

JSON Mode for Structured Data

You can force the model to output valid JSON by setting the response_format to json_object. This is useful for extracting structured data from unstructured text or generating configuration files. The model is tuned to adhere to this format when requested.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.unfilteredaichat.top/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);

JSON mode is part of the standard chat-completions endpoint. It works alongside other parameters like temperature and top_p. If the model fails to produce valid JSON, it may refuse the request or return malformed data, but the endpoint supports this feature for consistent structuring.

Function Calling Tools

The API supports function calling, allowing the model to output structured data that triggers external tools. You define tools in the request, and the model decides when to call them. This is useful for building agents that interact with other services.

• Tools: Define functions with names, descriptions, and parameters.
• Tool Choice: Specify tool_choice to force a tool call or allow the model to decide.

Copycurl https://api.unfilteredaichat.top/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."}]
  }'

Function calling is part of the uncensored AI API's feature set. It works with the same model that provides unfiltered text responses. There is no model routing; you are always using the same uncensored model for both text and tool use.

Crypto Payments Explained

Payments are handled entirely through cryptocurrency. You can top up your account with USDT on the TRC20 network or USDC on the Base network. The minimum top-up is $10, and the maximum is $500 per transaction. There are no fees for card processing or PayPal.

Bonus credit is added automatically: +5% for deposits of $50 or more, and +10% for deposits of $100 or more. Credit never expires, so you can top up when it suits you. No card is needed for the trial, which gives $0.50 valid for 7 days. Sign-up is via Google or email/password, and the API key is shown immediately.

Rate Limits and Best Practices

The API enforces specific limits to ensure stability. You can make 300 requests per minute per key and have 8 requests active simultaneously. The maximum request body size is 8 MB. Each account has one active API key; generating a new key replaces the old one.

Best practices include monitoring token usage to manage your prepaid credit effectively. Since errors are free, you can retry failed requests without cost. Use streaming for long outputs to improve user experience. The uncensored API is designed for developers who need a simple, reliable endpoint without complex routing or subscription fees.