Uncensored API
Unrestricted AI Models API
Get a reliable uncensored LLM with a 100,000-token context window, paying only for what you use with prepaid tokens and crypto.
- OpenAI-compatible POST endpoint
- Crypto top-ups only
- $0.50 trial credit
Test with one call
curl https://api.modelsaiunrestricted.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "List the top five open source models for local inference."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.modelsaiunrestricted.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.modelsaiunrestricted.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);Capabilities
OpenAI Compatible
Works with any standard OpenAI SDK by changing the base URL.
Uncensored Model
Answers without refusals for lawful adult and creative content generation.
Large Context
Supports 100,000 tokens for long documents and complex roleplay sessions.
Streaming Support
Real-time token streaming with usage data included in the final chunk.
JSON Mode
Enforce structured output formats using the response_format parameter for APIs.
Crypto Payments
Top up with USDT or USDC without linking a credit card.
Setup guide
Create Account
Sign in with Google or email to get your key instantly.
Add Credit
Top up with crypto and receive bonus credit on larger amounts.
Start Coding
Send requests to the chat-completions endpoint using your preferred SDK.
Common use cases
Creative Writing
Generate stories without content filters blocking mature or edgy themes.
Roleplay Bots
Run consistent characters with unrestricted memory and dialogue generation.
Data Extraction
Parse long texts using JSON mode for precise structured output.
API Integration
Replace OpenAI endpoints in existing apps with zero code changes.
How it works: 3-5 numbered steps from signup to the first answer
Start by creating your account using Google or a simple email.
Use Cases for Unrestricted AI Models
Our uncensored LLM enables precise creative writing and roleplay without artificial content filters. Developers integrate the NSFW API directly into applications for consistent, unfiltered narrative generation.
Roleplay Engines
Support complex character personas with 100,000 token context windows, maintaining long-term memory without unnecessary refusals.
Creative Drafting
Generate mature, unvarnished story drafts quickly using the standard OpenAI-compatible endpoint.
Research Analysis
Analyze controversial topics freely for internal projects without corporate moderation layers.
Migrate from OpenAI in Three Steps
Migrate from OpenAI in Three Steps
Switch your existing application to our uncensored LLM in under five minutes by updating your base URL and model ID. First, navigate to the “Get API key” page and sign in via Google or email to generate your unique credential. Second, paste that key into your SDK configuration. Finally, change your base_url to HTTPS://api.modelsaiunrestricted.com/v1 and set the model ID to "uncensored". Your code continues working with standard OpenAI-compatible parameters like temperature and top_p.
Cost Calculator: See How Far Your Tokens Go
Calculating your spend is straightforward with our prepaid token model. Input tokens cost $0.15 per 1M; output tokens are $0.50 per 1M. Errors and refusals incur zero charge, ensuring you only pay for delivered text. Prepaid credit never expires, so you can top up with USDT or USDC whenever needed. This transparent pricing lets you predict costs accurately without hidden monthly fees or complex subscription tiers.
Common Mistakes in the Uncensored LLM Niche
Developers often assume uncensored models output longer text by default, but our API limits responses to 16,000 tokens unless you specify max_tokens. Many also overlook that errors remain free while valid usage consumes prepaid credits. Another frequent error is sending requests exceeding the 8 MB body limit. Ensure your client handles streaming via SSE correctly, as token usage data appears only in the final chunk.
Who It Is For: Power Users and Creators
Who It Is For: Power Users and Creators
Power users building roleplay bots or creative projects need reliable, uncensored responses without complex filtering. Our API delivers a single robust model with 100,000-token context for long narratives. Creators who hate monthly fees prefer our prepaid token model. It is not for teams needing image generation or fine-tuning. Use it when you want direct, unfiltered text output via OpenAI-compatible SDKs.
Frequently asked questions
What are unrestricted AI models?
They are large language models that do not refuse lawful adult, fictional, or controversial topics. Our API serves one such model via the /v1/chat-completions endpoint. It supports streaming, function calling, and a 100,000-token context window for robust usage.
Does the API support streaming responses?
Yes, it supports Server-Sent Events (SSE) for streaming. You receive real-time tokens, and the final chunk includes total token usage. This allows you to display text instantly while maintaining the full context window of 100,000 tokens.
What payment methods are accepted?
We accept only crypto top-ups: USDT (TRC20) or USDC (Base). Amounts range from $20 to $500, with bonuses like 15% extra for $200 deposits.
Are prompts used for training?
No, your prompts are not used for training. We prioritize privacy by keeping your data internal. You can sign up with just an email, and your usage remains private without requiring a phone number or complex verification steps.
Is there a free trial available?
Yes, every new account gets $0.50 of trial credit valid for seven days. This allows you to test the uncensored model immediately before topping up with your preferred cryptocurrency for ongoing usage.
What are the request limits?
You can send 300 requests per minute and run eight concurrent requests per key. The maximum request body size is 8 MB. These limits ensure stable performance for high-volume applications without requiring complex enterprise-level scaling configurations.
Secure your API key
Sign up, grab the token, update your endpoint. Done.
