Uncensored LLM API

The Unrestricted AI API for Uncensored Responses

Get a reliable, OpenAI-compatible endpoint for uncensored responses without content refusals. Run our dedicated 64k context model for lawful adult use, fiction, or research.

Own GPU servers, no hidden filters
Pay-as-you-go, no monthly fees
64k context window, instant key

Get API key Read the docs

Try it in one request

curl https://api.unrestrictedaiapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

from openai import OpenAI

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

per 1M input tokens: $0.25
Output tokens / 1M: $1.00
token context: 64,000
trial credit: $0.50
requests per minute: 300

What you get

Uncensored Responses

Our model answers without refusing lawful adult, controversial, or fictional topics. It is tuned to deliver content without the typical corporate guardrails.

OpenAI Compatible

Drop it into your existing code using standard endpoints. Supports streaming via SSE and tool/function calling with the official SDKs.

Dedicated Infrastructure

We run our own open-weight model on dedicated GPU servers. This ensures consistent 64k context windows and no shared resource throttling.

Transparent Pricing

Pay only for what you use with prepaid credit. No subscriptions, no hidden fees, and credits never expire once purchased.

Instant Access

Developer First

Regenerate keys instantly, use standard HTTP methods, and get clear rate limits. No phone number or complex onboarding required.

How it works

Generate Your Key

Configure Your Client

Set your base URL to our endpoint and inject your API key into your SDK.

Send Requests

POST to the chat completions endpoint and receive uncensored text responses.

What people build with it

NSFW Content Generation

Generate adult fiction or roleplay without content filters blocking lawful topics. Perfect for creative writing tools needing unrestricted narrative freedom.

Security Research

Test model behavior with controversial prompts without immediate refusal. Ideal for red-teaming or analyzing uncensored model capabilities.

Chatbot Development

Build conversational agents that respond naturally to diverse topics. Avoid generic refusals for nuanced or mature user inputs.

Data Processing

Run large-scale text analysis with a 64k context window. Ideal for processing long documents or codebases without truncation.

Uncensored LLM API Overview

The unrestricted ai api provides a hosted, OpenAI-compatible endpoint for developers who need consistent, uncensored responses. Unlike generic proxies that route to various vendors, we run our own open-weight model on dedicated GPU servers. This ensures that you get the same model behavior every time, with a consistent 64,000 token context window. Our model is specifically tuned to answer without content refusals for lawful adult use, making it ideal for NSFW chatbots, fiction generation, and unrestricted data processing.

We do not offer image, audio, video, or embedding endpoints. This is a pure text API. If you need multimodal capabilities, this API is not for you. However, for text-heavy applications requiring no filters, this is the most reliable dedicated solution available.

OpenAI-Compatible Endpoints

Our API adheres strictly to the OpenAI chat-completions standard. You can use the official OpenAI SDKs or any compatible client by simply changing the base URL to https://api.unrestrictedaiapi.com/v1. We support streaming via Server-Sent Events (SSE) and function/tool calling for dynamic agent behaviors.

POST /v1/chat/completions: Send prompts and receive text responses. Supports streaming and tool use.
GET /v1/models: Retrieve available model information.

We do not support embeddings, fine-tuning, or image generation. If your workflow requires these, you will need to integrate additional services. Our focus is on delivering high-quality, uncensored text generation with minimal overhead.

Model Specifications & Context

Our model identifier is uncensored. It is an open-weight model hosted on our infrastructure, not a resell of GPT, Claude, or Gemini. This means you are getting a consistent experience without the variability of third-party routing. The model supports a massive 64,000 token context window, allowing you to pass large documents, codebases, or long conversation histories in a single request.

Each request is limited to an 8 MB body. You are limited to 300 requests per minute per API key. If you need higher throughput, you can regenerate your key or manage multiple keys. The model blocks sexual content involving minors, which is a hard limit applied regardless of your settings. For all other lawful adult content, refusals are minimal.

Pricing & Prepaid Credits

We use a transparent, pay-as-you-go model with no monthly fees. You preload credits and pay based on token usage. Input tokens cost $0.25 per 1M, and output tokens cost $1.00 per 1M. Credits never expire, so you can pause usage without losing your balance.

We offer bonuses for larger top-ups: +5% credit for $50+ and +10% for $100+. You can pay via card or crypto. New accounts receive $0.50 in trial credit valid for 7 days, no card required. This is not a free unlimited tier; you pay for what you use. If you need an SLA or SOC2 certification, we are not that service. We are a developer-focused, cost-effective API.

Questions and answers

Is this API truly uncensored?

Yes, our model is tuned to answer without refusing lawful adult, controversial, or fictional topics. The only hard limit is sexual content involving minors, which is always blocked. It does not refuse standard content based on political or social biases like generic models.

Can I use the OpenAI SDK with this API?

Absolutely. Our API is fully OpenAI-compatible. You can use the official OpenAI SDK for Python, Node.js, or other languages by setting the base URL to <code>https://api.unrestrictedaiapi.com/v1</code> and providing your API key.

What is the context window size?

Our model supports a 64,000 token context window. This includes both the prompt and the completion. This allows for processing large documents or maintaining long conversation histories without truncation.

Do I need a credit card for the trial?

No. You can sign up with just an email and password to receive $0.50 in trial credit valid for 7 days. No credit card is required to start testing the API.

Is my data used for training?

No. We do not use your prompts for training. Your data is processed to generate responses but is not used to improve our model. We prioritize privacy for developers who need to keep their data secure.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Get API key