Uncensored API
Uncensored LLM Leaderboard API
Get one top-ranked uncensored LLM leaderboard model via an OpenAI-compatible API with a 100,000-token context window for NSFW and creative work.
- Zero refusals for lawful adult content
- Crypto-only payments via USDT or USDC
- No card needed for $0.50 trial
Try with trial creditBrowse documentation
curl https://api.leaderboardllmuncensored.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "List the top 3 uncensored models for roleplay."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.leaderboardllmuncensored.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)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.leaderboardllmuncensored.com/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);Core features
- leaderboardllmuncensored.com › 01
OpenAI Compatible
Use your existing SDKs with our standard endpoint.
- leaderboardllmuncensored.com › 02
Large Context
Process 100,000 tokens per request easily.
- leaderboardllmuncensored.com › 03
Streaming Support
Real-time SSE streaming with full token usage.
- leaderboardllmuncensored.com › 04
JSON Mode
Force structured json_object responses for apps.
- leaderboardllmuncensored.com › 05
Tool Calling
Native function calling with tool_choice support.
- leaderboardllmuncensored.com › 06
Instant Access
Sign up with Google and get your key.
Setup workflow
Create Account
Sign in with Google or email instantly.
Add Crypto Credit
Top up with USDT or USDC securely.
Start Requesting
Send text to our API endpoint now.
Common use cases
NSFW Roleplay
Run adult chatbots without content filter interruptions.
Creative Writing
Generate unrestricted stories and scripts freely.
Data Extraction
Parse text without hallucinated refusals blocking you.
Model Testing
Benchmark uncensored models on standard leaderboards.
Moving from another OpenAI-compatible provider in three steps
Switch your client to our uncensored API in three steps. First, update your base_url to HTTPS://api.leaderboardllmuncensored.com/v1. Second, set model to uncensored and paste your key. Third, send a test request to /v1/chat/completions. That’s it. You now access a high-intelligence model without complex local setups or restrictive filters.
How it works: 3-5 numbered steps from signup to the first answer
Get your uncensored API key in seconds. 1. Sign up via Google or email. 2. Top up with USDT or USDC. 3. Call POST /v1/chat/completions. 4. Receive text. Start generating now.
Why 'uncensored LLM leaderboard' matters: Use cases for NSFW and creative work
Developers prioritizing the uncensored LLM leaderboard need APIs that preserve narrative nuance without artificial moral filtering. Our service delivers this through a single, high-intelligence model tuned for adult and creative content.
Roleplay Applications
Characters maintain consistent personalities across long contexts without sudden refusals.
Creative Writing
Authors generate raw, unvarnished prose suitable for mature themes.
Research & Data
Analyze controversial topics with a model that does not sanitize complex outputs.
Common mistakes people make in this niche and how to avoid them
Developers often assume all uncensored models handle 128k context windows identically, but our endpoint caps input at 100,000 tokens. This distinction prevents unexpected truncation during long roleplay sessions. Another frequent error is ignoring streaming, which delays response visibility. Always configure your SDK for SSE to receive tokens in real-time. Additionally, ensure you set max_tokens explicitly; omitting it defaults to 2,048 output tokens, potentially cutting off complex creative narratives prematurely.
Worked cost examples with token arithmetic that use only our prices
Worked cost examples with token arithmetic that use only our prices
Your total bill depends strictly on input and output token counts. A 50,000-token input prompt costs $7.50. Adding a 16,000-token response (maximum allowed) adds $8.00. The combined request totals $15.50. This calculation uses only our rates: $0.15 per million input tokens and $0.50 per million output tokens. Errors incur zero charges. Your prepaid credit covers the exact usage without hidden fees or monthly subscriptions.
Who uses it, in which real situations; and plainly who it is NOT for
Who uses it, in which real situations; and plainly who it is NOT for
Developers building NSFW chatbots, roleplay engines, and creative writing tools rely on our uncensored LLM API for direct, refusal-free text generation.
Teams use the 100,000-token context window for long-form narrative continuity without hitting content filters.
- Use it for: adult-themed roleplay, uncensored creative writing, and general-purpose text generation without restrictions.
- Avoid it if you need: image or audio generation, fine-tuning, or embeddings.
- It is not for: users requiring SLA guarantees, HIPAA compliance, or multi-model routing.
Support FAQ
What is the uncensored LLM leaderboard API?
It is a hosted service providing a single large language model via standard OpenAI-compatible endpoints. You send text in and receive text out without restrictive content filters. The system supports streaming, function calling, and JSON modes for flexible integration into your applications.
Does it handle NSFW chatbot requests?
Yes, the model does not refuse lawful adult, fictional, or controversial topics. It allows creative freedom while maintaining a hard limit on sexual content involving minors. This makes it ideal for NSFW chatbot implementations requiring uncensored output without complex local setups.
What is the context window size?
The context window is 100,000 tokens for both prompt and completion combined. You can request up to 16,000 output tokens per request. If you do not set the max_tokens parameter, the default output limit is 2,048 tokens.
How do I top up credit?
You top up using crypto only, specifically USDT on TRC20 or USDC on Base. Minimum payments start at $20, with bonuses of five percent or more for larger amounts. Prepaid credit never expires and is charged based on real token usage.
Are there monthly subscription fees?
No, there are no monthly fees or subscriptions. You pay only for the tokens you consume, with errors and refusals costing nothing. This prepaid model ensures you never pay for idle time or unused capacity in your integration.
Can I use standard OpenAI SDKs?
Yes, the API is fully compatible with official OpenAI SDKs and any OpenAI-compatible client. You simply update the base URL and provide your API key. This allows you to switch providers without rewriting your existing application code.
Get your key now
Register, copy the key, update base URL. Done.
