OpenAI-Compatible

Unmoderated ai API for Developers

Deploy an uncensored LLM via a standard OpenAI compatible API with a 100,000 token context window and transparent per-token pricing.

100,000 token context window
$0.15 per million input tokens
No card needed for trial

Get your key View documentation

Test with one call

curl https://api.aiunmoderated.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summit meeting notes from today"}]
  }'

from openai import OpenAI

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

Features

Standard Interface

Use POST /v1/chat/completions with existing OpenAI SDKs and clients without custom logic.

Uncensored Model

Get raw text outputs for lawful adult topics without standard content refusal filters.

Streaming Support

Receive token usage data in the final chunk via standard Server-Sent Events.

JSON Mode

Enforce structured outputs with the response_format json_object parameter for reliable parsing.

Function Calling

Define tools and control execution with tool_choice for automated agent workflows.

Zero Monthly Fees

Pay only for tokens used; prepaid crypto credit never expires or resets.

Setup process

Create Account

Fund Wallet

Top up with USDT or USDC to start using the uncensored LLM.

Send Request

Point your client to our base URL and model id uncensored.

Use cases

Uncensored Content Generation

Generate fiction, roleplay, or controversial topics without unexpected content blocks.

Data Extraction

Parse raw text from diverse sources using strict JSON mode outputs.

Agent Workflows

Build autonomous agents that call tools without human-in-the-loop refusals.

Long Context Analysis

Process large documents within the 100,000 token context window limit.

The Uncensored API Checklist: 6 Things to Verify Before You Commit

Verify strict endpoint compliance and true refusal behavior before integrating an unmoderated AI solution. Check for a single dedicated model id, not complex routing logic. Ensure prepaid crypto credits never expire. Confirm streaming via SSE and JSON mode support. Verify no hidden usage fees for errors. Test the 100,000 token context window. Validate the $0.15/$0.50 per 1M token pricing structure.

Who This API Is For (And Who Should Look Elsewhere)

Who This API Is For

Builders needing an uncensored LLM endpoint for lawful adult content, roleplay, or unrestricted data generation get exactly that without content refusals. Our openai compatible API delivers raw text outputs via a standard interface.

Developers prioritizing integration speed over marketing fluff.
Teams requiring 100,000-token context windows for long-form tasks.

Who Should Look Elsewhere

If you need image generation, embeddings, or fine-tuning, this is not your solution. We offer only text completions. Similarly, users expecting multi-vendor model routing or SLA guarantees should find a different provider.

unmoderated AI Use Cases: From Roleplay to Raw Data Generation

The uncensored LLM powers diverse applications by delivering raw, refusal-free text for creative and technical workflows.

Immersive Roleplay

Generate character dialogues that retain personality without sudden content blocks or sanitized responses.

Content Moderation Testing

Train filters using diverse, unrestricted samples that reflect real-world user behavior accurately.

Raw Data Extraction

Parse unstructured text from varied sources without losing context due to artificial safety layers.

Migrate from OpenAI or Claude in Three Simple Steps

Switching to our uncensored LLM requires only updating your base URL and model ID. First, replace your current endpoint with HTTPS://api.aiunmoderated.com/v1 in your SDK configuration. Second, change the model identifier to "uncensored" for text generation. Third, verify streaming and JSON mode work as expected. This openai compatible API accepts standard parameters like temperature and top_p. No complex routing logic is needed.

From Signup to First Token: How It Works in 5 Steps

Get your key. Use Continue with Google or email. No phone number required. The key appears instantly.
Set the base URL. Point your SDK to https://api.aiunmoderated.com/v1.
Configure the model. Set model to uncensored.
Send a request. Use POST /v1/chat/completions.
Receive text. Get uncensored output without content refusals for lawful adult use.

Common Integration Mistakes in the Uncensored Niche (And How to Avoid Them)

Developers often misconfigure the base_url or ignore the 100,000-token context window. Always verify your client points to https://api.aiunmoderated.com/v1 and send model: "uncensored". Do not assume streaming is enabled by default; set stream: true to receive SSE chunks. Remember that errors incur zero cost, but your prepaid credit never expires, so top up via crypto only. Finally, respect the 300 requests per minute limit to avoid throttling during high-volume generation tasks.

FAQ

What is unmoderated AI and how does it differ from standard LLMs?

It is an uncensored LLM that answers without content refusals for lawful adult use. Unlike standard models, it does not reject controversial or mature topics. The only hard limit is sexual content involving minors, which is always refused.

Does this openai compatible API support streaming responses?

Yes. The API supports streaming via Server-Sent Events (SSE). Token usage details are included in the last chunk of the stream, allowing you to monitor costs in real time as the model generates text continuously.

What is the cost structure for input and output tokens?

Input tokens cost $0.15 per 1 million tokens. Output tokens cost $0.50 per 1 million tokens. Errors and refusals are free, so you only pay for actual usage. Credit never expires.

Can I use this unrestricted chatbot for function calling?

Yes. The API supports function calling with tools and tool_choice parameters. You can also enforce JSON mode using response_format json_object, making it suitable for structured data generation without extra configuration.

How do I top up my prepaid credit?

Top up using crypto only: USDT (TRC20) or USDC (Base). Any whole amount from $20 to $500 is accepted. You receive bonus credit: +5% from $50, +10% from $100, and +15% from $200.

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.

Get your key now

Get your key