Uncensored API
Unrestricted llm models for uncensored generation
Get the unrestricted LLM models API that never refuses lawful adult content, featuring a 100k token context window for deep, uninterrupted roleplay.
- 100k token context window
- No training on prompts
- Zero refusal on adult topics
Test with one call
curl https://api.unrestrictedllmmodels.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Generate a JSON object with keys for user_id and role."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.unrestrictedllmmodels.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.unrestrictedllmmodels.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
- $0.15
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
Core capabilities
OpenAI Compatible
Drop-in replacement using standard endpoints and SDKs.
Streaming Support
Real-time token delivery via Server-Sent Events.
JSON Mode
Structured output for reliable programmatic integration.
Tool Calling
Native function execution with flexible choices.
Crypto Payments
Simple USDT or USDC top-ups only.
No Subscriptions
Pay per token with no monthly fees.
Uncensored API, open wallet, no refusals
Setup guide
Create Account
Sign up with Google or email instantly.
Get Key
Receive your API key immediately upon signup.
Start Coding
Send requests to the uncensored endpoint.
Community creations
NSFW Roleplay
Generate uncensored stories without unexpected content blocks.
Creative Writing
Explore mature themes freely in your drafts.
Data Analysis
Process large texts within the 100k limit.
API Integration
Connect to any OpenAI-compatible client easily.
Who needs unlimited text generation and who should skip the hype
Developers building NSFW chatbots or unrestricted AI writing tools get direct access to one uncensored model via an OpenAI compatible API.
- Use it for adult content generation without filters.
- Skip us if you need image or video generation.
Our service handles text only. We do not offer embeddings, fine-tuning, or multi-model routing. If you require complex data pipelines, look elsewhere. This is a simple text API.
Real token math: how much your uncensored stories actually cost
Your NSFW stories cost pennies per page. Input tokens run $0.15 per million; output tokens are $0.50 per million. A 5,000-word draft consumes roughly 6,700 input and 6,700 output tokens, totaling $0.00435. Errors and refusals incur zero charges. Prepaid credits never expire. You pay strictly for what you generate.
unrestricted LLM models: four concrete ways to use our API
uncensored roleplay and NSFW chatbot experiences
Our uncensored LLM handles adult themes without sudden refusals, enabling seamless creative writing sessions.
abliterated models for coding
Generate code with fewer restrictions. Use JSON mode for reliable parsing.
unrestricted search integration
Route queries to our API. Token usage is transparent.
uncensored AI for privacy
Your prompts stay private. No training data leaks.
From signup to first token in five simple steps
Start generating in minutes with our straightforward workflow.
- Visit the Get API key page and choose Continue with Google or enter your email.
- Receive your unique key instantly; no phone number required.
- Set your client's base URL to
https://api.unrestrictedllmmodels.com/v1. - Send a
POSTrequest using modeluncensored. - Receive unrestricted text output directly to your application.
Three common mistakes developers make with uncensored APIs
Developers often assume unlimited text generation means infinite context without checking limits. Our API enforces a strict 8 MB request body and caps concurrency at eight simultaneous requests per key. Another frequent error is ignoring the 16,000-token output ceiling; omitting max_tokens defaults to a mere 2,048 tokens. This truncation ruins long NSFW roleplay sessions. Always configure your client to respect these constraints. Streaming responses via SSE help manage large outputs effectively.
Switch from OpenAI or Claude to our API in three steps
Switch from OpenAI or Claude to our API in three steps
Change your base URL to HTTPS://api.unrestrictedllmmodels.com/v1 and update the model ID to “uncensored”. Your existing OpenAI SDK code works immediately. Requests route directly to our single, abliterated model without complex aggregators or hidden fees. You gain unrestricted creative freedom while maintaining strict data privacy since prompts are never used for training. Start with a free trial today.
Common questions
What is an unrestricted LLM models API?
It is a hosted, OpenAI-compatible chat-completions API serving one uncensored large language model. You get direct text-in, text-out access with no hidden content filters for lawful adult use or creative writing.
Does the API use my prompts for training?
No, your prompts are never used for training data. An account needs only an email, ensuring strict data privacy while you generate unlimited text without your creative work becoming part of a larger dataset.
How do I pay for the API?
You top up using crypto only, specifically USDT on TRC20 or USDC on Base. Prepaid credit is charged by real token usage, with no monthly fees, and errors or refusals are completely free to use.
What is the context window limit?
The context window is 100,000 tokens for both prompt and completion together. You can generate up to 16,000 tokens per request, or 2,048 if you do not explicitly set the max_tokens parameter in your calls.
Are there any hard content limits?
Yes, a hard content limit always applies to sexual content involving minors. Requests of that kind are refused, but all other lawful adult, fictional, or controversial topics are generated without the typical corporate gatekeeping refusals.
How do I start using the service?
Sign up using Continue with Google or an email password on the Get API key page. Your key is shown immediately, allowing you to make your first request to the base URL without needing a phone number.
Generate your key now
Sign up, copy the token, update your endpoint. Done.
