EN ▾

Start with trial credit

Email and password, key on screen right away.

https://api.uncensoredllmhub.com/v1

Hosted API

Uncensored LLM API for Developers

Integrate an uncensored large language model into your application via a standard OpenAI-compatible endpoint. Get text in and text out without local GPU management or content refusals for lawful adult use.

Get API keyRead the docs

  • OpenAI-compatible API
  • 100k context window
  • No subscription required
  • $0.15per 1M input tokens
  • $0.50Output tokens / 1M
  • 100,000token context
  • $0.50trial credit
  • 300requests per minute

Try it in one request

curl https://api.uncensoredllmhub.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

  • Standard Interface

    Use the exact same SDKs and endpoints as OpenAI. Change one line of code to point to our base URL and start sending requests immediately.

  • Uncensored Output

    The model answers without refusing lawful adult, fictional, or controversial topics. It is not GPT, Claude, or any other vendor model.

  • Streaming & Tools

    Supports Server-Sent Events for streaming responses and tool/function calling for complex application logic.

  • Transparent Pricing

    Pay only for what you use with prepaid credit. No monthly fees, no subscriptions, and credits never expire.

  • Privacy Focused

    Your prompts are not used for training. Account setup requires only an email and password.

  • Simple Limits

    300 requests per minute per key with an 8 MB request body limit. One key per account, regeneratable at any time.

How it works

  1. Get Your Key

    Sign up with an email and password to receive your API key instantly.

  2. Update Base URL

    Point your existing OpenAI-compatible client to https://api.uncensoredllmhub.com/v1.

  3. Send Requests

    Send text to the uncensored model and receive reliable, unrefused outputs.

What people build with it

  • Content Generation

    Generate creative fiction or roleplay scenarios without the model hedging or refusing based on standard safety filters. Ideal for applications needing raw, unfiltered narrative output.

  • Coding Assistance

    Use an uncensored coding LLM to get direct answers to complex programming questions without unnecessary conversational filler or moralizing about code quality.

  • Research & Analysis

    Process large documents within the 100k context window to extract insights or summarize text without the model refusing to process specific topics.

  • Developer Integration

    Replace expensive or restrictive API providers in your stack with a predictable, pay-as-you-go uncensored alternative that supports streaming and tools.

What is an Uncensored LLM?

An uncensored large language model is designed to answer questions and generate text without refusing based on standard content policies. While many commercial models will decline to discuss certain topics, produce overly cautious responses, or refuse lawful adult content, our model is tuned to provide direct answers for a wide range of subjects.

This is particularly useful for developers building applications where the output needs to be raw and unfiltered, such as creative writing engines, roleplay bots, or specialized research tools. It is not GPT, Claude, Gemini, Grok, or DeepSeek; it is an open-weight model run on our own infrastructure, optimized to minimize refusals while maintaining high quality.

Why Use a Hosted API?

Running an uncensored model locally requires significant GPU resources and technical setup. Our hosted API removes that burden by providing a standard OpenAI-compatible endpoint. You can use the official OpenAI SDKs or any compatible client by simply changing the base URL and API key.

The API supports streaming via Server-Sent Events (SSE) and tool/function calling, making it suitable for complex applications. You get a 100,000 token context window for both prompt and completion, allowing you to process substantial amounts of data in a single request.

Who This Is NOT For

If you need image generation, audio processing, video creation, or embeddings, this API is not for you. We do not offer multi-modal capabilities, fine-tuning, or model routing between different vendors. We strictly provide text-in, text-out functionality.

Additionally, if you require enterprise-grade SLAs, SOC2/HIPAA certifications, or on-prem deployment, our simple pay-as-you-go service may not meet your compliance needs. We are an independent service, not a reseller of another company's model, and we do not guarantee uptime percentages or specific latency targets.

Pricing: Pay-As-You-Go

We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. There are no monthly subscriptions or hidden fees. You preload credit, and it never expires. You can top up from $20 using crypto (USDT on TRC20, USDC on Base).

We offer bonus credits to encourage higher usage: receive a +5% bonus on balances of $50 or more, +10% bonus on balances of $100 or more, +15% from $200. This transparent pricing structure allows you to scale your usage without worrying about sudden cost spikes or tier limits.

Questions and answers

Is this model the same as GPT-4 or Claude?

No. Our model is an open-weight model run on our own GPU servers. It is tuned to answer without content refusals for lawful adult use, distinguishing it from major vendor models like GPT, Claude, Gemini, Grok, or DeepSeek. It is not a resold version of any other vendor's model.

What is the context window size?

The context window is 100,000 tokens, covering both the prompt and the completion. This allows you to process large documents or maintain long conversations within a single request.

Do you offer image or audio generation?

No. We strictly offer a text-based API. There are no embeddings, image generation, audio, or video capabilities. The endpoints are POST /v1/chat/completions and GET /v1/models.

How does the trial credit work?

You get $0.50 of trial credit, one per person, valid for 7 days. No card is needed to sign up or claim the trial. The credit is used to test the API before you add funds.

What content is blocked?

A hard content limit always applies: no sexual content involving minors. Requests of that kind are blocked. All other lawful adult, fictional, or controversial topics are generally not refused.

Your key is one form away

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

Get API key

https://api.uncensoredllmhub.com/v1