Uncensored LLM API

AI uncensored info: The Uncensored LLM API

Deploy the uncensored AI API with a 100,000-token context window via our OpenAI-compatible endpoint. No subscriptions required.

Get API key View documentation

Test via single request

curl https://api.aiuncensoredinfo.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

from openai import OpenAI

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

Crypto-only top-ups

No card needed

$0.50 trial credit

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

Drop-in replacement using standard base_url and models.

100k Context Window

Process extensive prompts with full conversation history.

Streaming via SSE

Real-time token delivery with usage data in chunks.

JSON Mode

Force structured output with response_format json_object.

Function Calling

Support tools and tool_choice for dynamic actions.

No Training Data

Prompts stay private and are never used for training.

Setup guide

Create Account

Top Up Crypto

Add funds via USDT or USDC for bonus credit.

Integrate SDK

Update base_url and start sending chat completions.

Common use cases

NSFW Roleplay

Generate unfiltered adult content without standard refusals.

Coding Assistance

Uncensored coding API for unrestricted technical discussions.

Research Analysis

Analyze controversial topics without content moderation filters.

Creative Writing

Produce unhinged AI narratives with full creative freedom.

AI uncensored info: Your Gateway to Unrestricted Content Generation

AI uncensored info delivers an open-weight LLM endpoint that skips content filters for lawful adult topics, roleplay, and unfiltered creative writing.

NSFW Roleplay Simulation

Generate nuanced character dialogues without arbitrary refusal blocks.

Uncensored Coding API

Query the model for raw technical explanations without tone policing.

Unhinged AI Creative Writing

Produce unfiltered narratives that ignore standard safety guardrails.

Uncensored LLM Leaderboard Testing

Evaluate model behavior on controversial prompts with zero bias.

Real Cost Breakdown: What Your Tokens Actually Buy

Your tokens buy exactly what you consume, nothing more. We charge $0.15 per million input tokens and $0.50 per million output tokens. Errors and refusals remain free. This prepaid, crypto-only system ensures transparent pricing without hidden subscription fees. You only pay for the text generated by our uncensored LLM, making it ideal for high-volume, unfiltered content workflows where every cent counts.

H2: Who Should Use This API (And Who Should Look Elsewhere)

Use this uncensored LLM API for NSFW roleplay, unfiltered coding, or unrestricted text generation. It serves developers needing an OpenAI-compatible endpoint without content refusals. Integrate immediately by setting the base URL to https://api.aiuncensoredinfo.com/v1 and using the uncensored model ID. Streaming via SSE works for real-time output. Look elsewhere if you need image generation, embeddings, or audio support. This service provides one specific large language model for text-to-text tasks, not a multi-modal suite or enterprise-grade infrastructure.

The Uncensored Provider Checklist: 6 Essential Criteria

Verify these six criteria before committing your budget.

Confirm a single, purpose-built model without hidden routing layers.
Check for transparent token pricing without subscription locks.
Ensure crypto-only top-ups via USDT or USDC.
Validate OpenAI compatibility with standard SDKs.
Confirm no content refusals for lawful adult topics.
Ensure prompts are not used for training.

Developer Questions: Community Insights and Honest Answers

The uncensored LLM API handles adult content without arbitrary refusals, though it strictly blocks sexual content involving minors. You can stream responses via Server-Sent Events to receive token usage details in the final chunk. Integration is immediate; simply update your base_url to our hosted endpoint and send requests to the standard chat-completions path. The model supports function calling and JSON mode for reliable parsing. Errors and refusals incur no charge, ensuring you only pay for actual token usage.

H2: How We Compare: 5 Concrete Differences from Standard Providers

We strip away enterprise bloat, offering a single uncensored model with crypto-only top-ups and transparent token pricing. Unlike standard providers, we charge $0.15 per 1M input tokens and $0.50 per 1M output tokens, with no hidden fees. This API is not a reseller of GPT or Claude; it is a dedicated, open-weight model designed for unrestricted generation without subscription complexity.

Frequently asked questions

What is AI uncensored info and how does it differ from standard models?

It is a dedicated uncensored LLM API designed for unrestricted content generation. Unlike standard models, it does not refuse lawful adult or controversial topics. This API serves as a drop-in replacement for existing OpenAI-compatible codebases without requiring major architectural changes.

Which payment methods do you accept?

Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.

What payment methods are accepted for topping up credit?

Credit is topped up exclusively via crypto, specifically USDT on TRC20 or USDC on Base. You can deposit any whole amount from $20 to $500.

How much does the uncensored LLM API cost per token?

Pricing is $0.15 per million input tokens and $0.50 per million output tokens. Errors and refusals incur no charge. This transparent model ensures you pay only for actual token usage, with prepaid credit that never expires for your convenience.

Can I stream responses and use tools like other OpenAI models?

Yes, the API supports streaming via Server-Sent Events and function calling. It also offers JSON mode and parameters like temperature and top_p. These features make it a fully functional OpenAI-compatible endpoint for complex application integrations and real-time data processing.

Is there a limit on the context window for long conversations?

The model supports a context window of 100,000 tokens for prompt and completion combined. You can generate up to 16,000 tokens per request. This large capacity ensures consistent performance even during extended interactions or processing lengthy documents efficiently.

Retrieve your API key

Get API key