EN ▾
Get API key

Pay Per Token

Unlimited AI API: Uncensored Text Generation

Get an uncensored LLM API for text generation with transparent per-token pricing and no monthly fees. Use our OpenAI-compatible endpoint to stream responses or call tools without content refusals.

  • $0.15 / 1M input tokens
  • $0.50 / 1M output tokens
  • No monthly fees

Try it in one request

curl https://api.unlimitedaiapi.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."}]
  }'

What you get

OpenAI Compatible

Drop this API into any OpenAI SDK or client by changing the base URL and API key. Supports streaming via SSE and tool/function calling out of the box.

Single Uncensored Model

We serve one dedicated uncensored large language model tuned for lawful adult use. It does not refuse controversial, technical, or mature topics, except for sexual content involving minors.

Transparent Pricing

Pay only for what you use. Input tokens cost $0.15 per million and output tokens cost $0.50 per million. Prepaid credit never expires.

Simple Setup

Sign up with just an email and password. Get your API key immediately without needing a credit card or phone number for the trial.

No Vendor Lock-in

We are an independent service. We do not route through other vendors or proxy services. You get direct access to our uncensored model on our own GPU servers.

Privacy First

Your prompts are not used for training. We keep your account simple with just an email and password, and you can regenerate your API key at any time.

How it works

Sign Up

Create an account with your email and password to get immediate access to your API key and trial credit.

Integrate

Update your client's base URL to https://api.unlimitedaiapi.com/v1 and set your API key.

Generate Text

Send a POST request to /v1/chat/completions with model 'uncensored' and receive streamed or standard text responses.

What people build with it

Content Creation

Write stories, scripts, or articles without worrying about standard content filters blocking creative or mature themes. Get raw text output for your publishing pipeline.

Data Processing

Extract structured data from unstructured text using tool calling capabilities. The model handles complex instructions without refusing due to topic sensitivity.

Research & Analysis

Ask controversial or technical questions without getting polite refusals. The model is tuned to answer directly, providing unbiased outputs for your research needs.

Chat Applications

Build chat interfaces that feel more human and less restricted. Use the 100k context window to maintain long conversations without losing context.

Why Uncensored Matters

Most LLMs are tuned to be helpful, harmless, and honest, which often means they refuse to discuss mature, controversial, or niche topics. Our uncensored LLM API is tuned to answer without content refusals for lawful adult use. This means you can generate text on a wider range of subjects without the model deciding it's 'too spicy' or 'too political' for you.

However, 'uncensored' does not mean 'no rules'. We have one hard content limit that always applies: we block requests involving sexual content involving minors. Everything else is fair game. This makes our API ideal for developers who need raw, unfiltered text output for creative writing, roleplay, or data analysis where standard filters might disrupt the flow.

OpenAI Compatible Endpoint

Our API is designed to be a drop-in replacement for the OpenAI API. We support the standard POST /v1/chat/completions endpoint and GET /v1/models. You can use the official OpenAI SDKs or any OpenAI-compatible client by simply changing the base URL to https://api.unlimitedaiapi.com/v1 and providing your API key.

We support streaming responses via Server-Sent Events (SSE) and tool/function calling. This means you can build complex applications that interact with other systems. The model ID you must send is uncensored. It is an open-weight model run on our own GPU servers, not a rebranded GPT or Claude model.

Transparent Pricing

We believe in simple, predictable costs. Our pricing is $0.15 per 1 million input tokens and $0.50 per 1 million output tokens. There are no hidden fees, no request-based pricing, and no monthly subscriptions. You pay for the tokens you use.

You can top up your account with a minimum of $20 using crypto (USDT or USDC). We offer bonus credits: +5% when you add $50, +10% when you add $100, and +15% when you add $200. Your prepaid credit never expires. New accounts get $0.50 in trial credit valid for 7 days, with no card needed. This makes it easy to test the API before committing. Claim this credit with one click on your API key page.

Not For Everyone

This API is for developers who want a simple, low-cost text generation tool. It is not for you if you need embeddings, image generation, audio, video, or fine-tuning. We do not offer model routing between different vendors; we serve one dedicated uncensored model. If you need high availability guarantees like SLA percentages, SOC2/HIPAA/ISO certifications, or on-prem deployment, this is not the right choice. We are a utility service, not an enterprise platform.

Questions and answers

Is this the same as ChatGPT?

No. We serve a dedicated uncensored large language model that is not GPT, Claude, Gemini, or any other vendor's model. It is an open-weight model tuned for fewer refusals. While it is compatible with the OpenAI API format, it is a different model with different characteristics.

What is the context window size?

The model supports a context window of 100,000 tokens for both prompt and completion. This allows for long conversations and large document processing.

Do I need a credit card to start?

No. You can sign up with just an email and password. New accounts receive $0.50 in trial credit valid for 7 days, with no card required. Claim this credit with one click on your API key page. You can add funds later via crypto (USDT or USDC).

Are my prompts used for training?

No. We do not use your prompts for training. Your data remains private. You can also regenerate your API key at any time to revoke access to the old one.

What content is blocked?

We have one hard content limit that always applies: sexual content involving minors. All other lawful adult, fictional, or controversial topics are allowed. The model is tuned to answer without content refusals for these topics.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Get API key