EN ▾
Get API key

Transparent LLM Data

Uncensored LLM API Leaderboard

Compare uncensored model rankings and get immediate developer access to a single, refusal-free large language model with predictable token pricing.

  • 100k context window
  • $0.15 per 1M input tokens
  • $0.50 trial credit

Try it in one request

curl https://api.uncensoredllmleaderboard.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."}]
  }'
per 1M input tokens
$0.15
Output tokens / 1M
$0.50
token context
100,000
trial credit
$0.50
requests per minute
300

What you get

  1. Open-Weight Model

    Runs an open-weight model tuned to answer without content refusals for lawful adult use, ensuring high-context responses.

  2. OpenAI-Compatible

    Use standard OpenAI SDKs by changing the base_url and API key; supports streaming via SSE and tool/function calling.

  3. Predictable Pricing

    Pay-as-you-go prepaid credit with no monthly fees or subscriptions; credits never expire and top-ups offer bonus credit.

  4. 100k Context Window

    Handle large prompts and completions within a 100,000 token window, ideal for long-document analysis and complex tasks.

  5. Simple Authentication

    Sign up with email and password to get an API key immediately; regenerate keys anytime to revoke access to the old one.

  6. Privacy Focused

    Prompts are not used for training, and no phone number or credit card is required to start with the trial credit.

How it works

  1. Sign Up

    Create an account with just an email and password to receive your API key instantly.

  2. Configure SDK

    Update your client configuration to point to our base_url and set your new API key.

  3. Send Requests

    Start sending POST requests to /v1/chat/completions with the model id "uncensored".

What people build with it

  • Long Document Analysis

    Process entire books or technical manuals in a single request thanks to the 100k context window. Extract key insights without losing context from earlier sections.

  • Creative Writing

    Generate stories or scripts without unwanted refusals for mature or controversial themes. Maintain narrative continuity over long-form outputs.

  • Security Research

    Prompt the model to identify vulnerabilities or generate examples without standard safety filters blocking technical jargon. Useful for red-teaming scenarios.

  • Data Extraction

    Parse structured data from unstructured text using function calling capabilities. Route responses directly into your application logic.

Why Leaderboard Matters

Most llm leaderboard sites show scores but hide the actual cost to use those models. We provide a transparent view of model openness and direct pricing data. This allows developers to compare options based on real utility, not just benchmark numbers. You can see exactly what it costs to process tokens, ensuring no surprises when scaling your application.

Our approach focuses on the data that matters for production: context length, token rates, and model behavior. By aggregating this information, we help you make informed decisions about which model fits your specific use case. This transparency is crucial for power users who need to predict expenses accurately.

The Uncensored Advantage

Our hosted API serves a single open-weight model tuned to answer without content refusals. This means you can explore adult, controversial, or technical topics without the model saying 'I can't do that' for lawful content. It is not GPT, Claude, or any other vendor model; it is an independent run on our servers.

What is not for: If you need embeddings, image generation, or multiple model routing, this is not the right API. We focus strictly on text completions with a 100k context window. We do not offer SLA guarantees, SOC2 certifications, or fine-tuning services. If you need enterprise compliance features, look elsewhere.

API Specs at a Glance

The API is OpenAI-compatible, meaning you can use your existing SDKs with minimal changes. Simply update the base_url and api_key. The model id is "uncensored". We support streaming via Server-Sent Events (SSE) and tool/function calling for structured outputs.

  • Endpoint: POST /v1/chat/completions
  • Models Endpoint: GET /v1/models
  • Context Window: 100,000 tokens
  • Rate Limit: 300 requests per minute per key
curl https://api.uncensoredllmleaderboard.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."}]
  }'

Pricing Transparency

We believe in simple, upfront costs. There are no monthly fees or subscriptions. You pay only for the tokens you use with prepaid credit that never expires. Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. This clarity helps you budget for your LLM usage without hidden fees.

You can top up from $20 by crypto (USDT on TRC20, USDC on Base). Bonus credit is available for larger deposits: +5% bonus from $50 and +10% bonus from $100. New accounts receive $0.50 in trial credit for 7 days, no credit card required.

from openai import OpenAI

client = OpenAI(base_url="https://api.uncensoredllmleaderboard.com/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)

Questions and answers

Is this the same as GPT-4 or Claude?

No. Our model is an open-weight model run on our own GPU servers. It is tuned for uncensored responses but is distinct from proprietary models like GPT, Claude, or Gemini. Check vendor documentation for their specific capabilities.

How do I start using the API?

Sign up with an email and password to get an API key instantly. Use the key with any OpenAI-compatible SDK by setting the base_url to our API endpoint. You can start immediately with the $0.50 trial credit. Claim this credit with one click on your API key page.

Do you use my prompts for training?

No. Prompts sent to our API are not used for training purposes. Your data remains private, and we do not sell or share your conversation data for model improvement.

What is the context window size?

The API supports a 100,000 token context window for both prompt and completion. This allows you to process large documents or maintain long conversation histories effectively.

Can I use this for commercial projects?

Yes. There are no restrictions on commercial use provided the content is lawful. The only hard limit is on sexual content involving minors, which is always blocked. You can scale usage by topping up your prepaid credit.

Your key is one form away

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

Get API key