Uncensored LLM API

Unrestricted chatbot API for developers

Integrate one pure uncensored model into your app with a standard OpenAI compatible API, no content filters and a 100k token context window.

Create key View documentation

POST /v1/chat/completions
Streaming via SSE
No subscription fees

curl https://api.chatbotunrestricted.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Fetch current temperature in Tokyo."}]
  }'

from openai import OpenAI

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

$0.15per 1M input tokens

$0.50Output tokens / 1M

100,000token context

$0.50trial credit

300requests per minute

Features included

OpenAI Compatible

Drop into existing code by changing base_url and your API key.

Uncensored Output

Receive raw responses without policy refusals for lawful adult content.

Function Calling

Supports tools, tool_choice and strict JSON mode for reliability.

Streaming Support

Get tokens via SSE with usage data in the final chunk.

Crypto Payments

Top up with USDT or USDC and get bonus credit instantly.

Developer First

Simple signup with Google or email and immediate key access.

Integration steps

Create Account

Sign up with Google or email to get your API key.

Add Credit

Top up with crypto and start using the uncensored model.

Integrate Code

Update your base_url and send requests to the API.

Built with this

Roleplay Stories

Generate unrestricted narratives without content filters blocking creative details.

Research Analysis

Process large documents with a 100k token context window.

Data Extraction

Use JSON mode to parse structured data from text reliably.

API Development

Test your app with a standard compatible endpoint quickly.

Why this API stands apart from typical alternatives

It delivers a single, uncensored model via standard endpoints without multi-model routing overhead.

Feature	Typical Multi-Model Proxy	Our API
Model Selection	Multiple vendors with complex routing logic	One dedicated uncensored LLM
Endpoints	Embeddings, images, audio, text	Only chat-completions
Complexity	High configuration requirements	Drop-in OpenAI SDK compatibility
Focus	Broad feature set	Raw capability and low latency
Pricing	Variable per model	Fixed transparent token rates
Integration	Requires adapter layers	Direct base_url override

From signup to first token: how it works

Start by creating your account via Google or email.

Get your key: The API key displays immediately on the dashboard.
Configure your SDK: Set base_url to https://api.chatbotunrestricted.com/v1.
Send a request: POST to /v1/chat/completions with model uncensored.

Receive raw, unrestricted text output without subscription locks.

Use cases for the unrestricted chatbot

It powers fluid roleplay, raw security research, and unfiltered creative writing without policy refusals.

Advanced Roleplay

Models handle complex characters and explicit scenarios naturally, avoiding the stiff “yes/no” refusals common in standard providers.

Safety Research

Engineers probe edge cases in a single, uncensored LLM API instance without worrying about sudden content filters.

Content Generation

Writers get direct access to mature themes for novels or scripts, ensuring the output matches the tone exactly.

Common pitfalls in the uncensored AI niche

Developers often overestimate context handling or assume model routing replaces actual capability. Many wrappers add latency and obscure raw responses. Our API offers a single uncensored model with a 100,000-token window and no subscription locks. Avoid complexity by using standard OpenAI SDKs directly. Streaming, JSON mode, and tools work out-of-the-box. Focus on integration speed rather than feature bloat.

Migrate from your current provider in three steps

Switch to our uncensored LLM API by updating your base URL and API key in under five minutes.

Generate a new key via our signup page.
Replace your existing base URL with https://api.chatbotunrestricted.com/v1.
Set the model ID to uncensored.

This standard OpenAI-compatible setup ensures immediate integration with your existing SDKs without code refactoring.

Real cost examples: token arithmetic and pricing

The uncensored LLM API charges $0.15 per million input tokens and $0.50 per million output tokens. A typical 2000-token request costs $0.00035. Errors and refusals incur no charge. Prepaid credits never expire. You only pay for actual usage without monthly fees or hidden subscription locks. This transparent model ensures predictable expenses for high-volume developer integrations.

Common questions

What is an unrestricted chatbot API?

It is a hosted, OpenAI-compatible service serving one uncensored large language model via standard endpoints. Text input yields text output without content refusals for lawful adult use. You can integrate it using the official OpenAI SDKs by updating the base URL.

Does it support image or audio generation?

No. This API serves text only. It provides POST /v1/chat/completions and GET /v1/models endpoints. There are no embeddings, image, audio, or video generation capabilities. It is strictly a text-in, text-out service for language processing.

How much does it cost per million tokens?

Input tokens cost $0.15 per million, while output tokens cost $0.50 per million. Prepaid credit is charged by real usage, and errors are free. Credit never expires, so you only pay for what you actually consume.

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 is the maximum context window size?

The model supports a 100,000-token context window for prompt and completion combined. You can request up to 16,000 output tokens per request. If you do not set max_tokens, the default output limit is 2,048 tokens.

Are prompts used to train the model?

No. Your prompts are not used for training purposes. The service maintains privacy by keeping your data separate from the training set. You can use the API for sensitive or proprietary content without worrying about data leakage.

Get your key now

Sign up, grab the key, update the base URL. That is all.

Create key