Uncensored API

Lite llm uncensored api

Get the uncensored LLM API that never blocks lawful adult content, supports a 100k token context window, and starts with $0.50 trial credit.

POST /v1/chat/completions endpoint
100,000 token context window
$0.15 per 1M input tokens

Try with trial credit View documentation

Test with a single request

curl https://api.llmlite.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list available models via get request"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.llmlite.cc/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.llmlite.cc/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);

per 1M input tokens: $0.15
Output tokens / 1M: $0.50
token context: 100,000
trial credit: $0.50
requests per minute: 300

Core features

OpenAI Compatible

Works with official OpenAI SDKs by changing base_url and API key.

No Content Blocks

Uncensored model answers without refusals for lawful adult and controversial topics.

Prepaid Crypto Credit

Pay with USDT or USDC; credit never expires and no card needed.

Fast Streaming

Stream responses via SSE with token usage reported in the last chunk.

JSON Mode

Force structured output with response_format json_object for reliable parsing in apps.

Simple Limits

300 requests per minute per key with 8 MB request body limit.

Setup guide

Sign Up

Continue with Google or email to get your API key instantly.

Top Up

Add crypto credit starting from $20 to activate your account balance.

Integrate

Set your base_url and start sending requests to the uncensored model.

Use cases

NSFW Chatbots

Deploy uncensored chatbots that handle adult content without unexpected content filters.

Creative Writing

Generate unrestricted fiction and roleplay scenarios with full creative freedom.

Data Extraction

Parse large documents with a 100k context window for deep analysis.

Dev Tools

Power developer tools with a reliable, open-weight API for any task.

Why most proxies block your NSFW requests (and how we don't)

Proxies block NSFW requests because they route through models with built-in refusals, adding latency and uncertainty. We serve one uncensored LLM directly from our servers, ensuring lawful adult content never triggers a refusal. This eliminates the middleman layer that filters your prompts. You get consistent, unfiltered outputs without the overhead of managing multiple model endpoints or waiting for secondary moderation filters to decide if your request is valid.

lite LLM: The uncensored backbone for your next project

Our uncensored LLM API serves content without the typical refusals that plague standard models, making it the reliable backbone for your next project.

Direct Integration

Connect instantly using standard OpenAI SDKs. Change the base URL and you are live. No middleware required.

High Context

Process 100,000 tokens in a single window. Keep your entire conversation history in memory without losing context.

Fast Streaming

Receive tokens via SSE with real-time usage updates. Your users see text appear instantly.

No Surprises

Prepaid credit never expires. Errors cost nothing. You only pay for tokens actually used.

Migrate from OpenAI in three lines of code

Switch to our uncensored LLM by updating your base URL and API key. base_url becomes https://api.llmlite.cc/v1 and model is set to uncensored.

Update your SDK configuration.
Replace the model ID.
Start generating.

The rest of your code stays the same. You get an openai compatible API that never refuses lawful adult content. It is a drop-in replacement for your current setup.

The NSFW API checklist: 7 things to verify before you buy

Verify that the model truly ignores refusals, not just the proxy layer.

Confirm 100,000-token context windows support long sessions.
Ensure strict base_url compatibility with your OpenAI SDK.
Check that streaming via SSE returns token usage.
Verify no hidden fees for standard parameters like temperature.
Confirm crypto-only top-ups match your budget needs.
Check 300 requests per minute limits for your scale.

Test with a $0.50 trial first.

Run the numbers: Real token math for your budget

Costs scale strictly with token volume at $0.15 per million input and $0.50 per million output tokens.

A 5,000-token prompt with 2,000 tokens generated costs $0.00175.
Heavy streaming sessions add up quickly, but errors remain free.

Prepaid credit never expires, so you pay only for what you consume without monthly subscriptions.

Developers ask: Ollama fallbacks, LiteLLM routing, and speed

Our API handles concurrent requests directly, bypassing the overhead of self-hosted LiteLLM proxies. You get predictable latency without managing your own GPU clusters or Ollama fallback chains. We support standard OpenAI-compatible streaming via SSE, so you can integrate instantly using your existing SDK code. Unlike local setups that choke under load, our uncensored model serves requests at scale. You can even switch from OpenAI in three lines of code without touching your app logic.

Frequently asked questions

What is lite LLM and how does it differ from standard models?

Lite LLM is an uncensored API serving one open-weight model tuned to answer without refusals. It returns text only via standard endpoints. Errors are free and credit never expires for your projects.

Is the uncensored AI output truly unfiltered for adult content?

Yes, the model does not refuse lawful adult, fictional, or controversial topics. It blocks only sexual content involving minors. You get consistent text output without arbitrary content blocks during your sessions.

How do I connect the API using the official OpenAI SDK?

You change the base_url to HTTPS://api.llmlite.cc/v1 and set your key. The endpoint is POST /v1/chat/completions. This works with any OpenAI-compatible client for immediate integration into your codebase.

What is the context window limit for long conversations?

The context window is 100,000 tokens for prompt and completion together. You can output up to 16,000 tokens per request. This allows for substantial data processing in single API calls.

Does the prepaid credit expire after I top up?

No, your paid credit never expires regardless of usage frequency. You can top up with crypto anytime. Errors and refusals do not consume your balance for accurate billing.

Can I use the API for function calling and JSON mode?

Yes, it supports function calling, tool_choice, and JSON mode. You can stream responses via SSE. Parameters like temperature and top_p are fully configurable for your specific needs.

Generate your API key

Try with trial credit View documentation