Raw LLM Power
Unhinged ai API for Developers
Get the uncensored LLM API with a 100k token context window and streaming support for your most demanding creative applications.
- OpenAI-compatible endpoints
- Prepaid crypto billing
- Function calling support
Test via single call
curl https://api.aiunhinged.cc/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Generate a JWT token valid for 1 hour"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.aiunhinged.cc/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.aiunhinged.cc/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);Core capabilities
Community projects
From Signup to First Token: Your 3-Step Integration
Get your uncensored LLM API key in seconds and start sending requests immediately.
- Sign up: Use Google or email to create an account. No phone number required. You receive a single active API key instantly.
- Add credit: Top up with USDT (TRC20) or USDC (Base). Minimum $20. Credits never expire.
- Integrate: Point your OpenAI-compatible SDK to
https://api.aiunhinged.cc/v1. Send a POST request to/chat/completionswith modeluncensored. Pay only for tokens used at $0.15 per 1M input and $0.50 per 1M output.
Who Needs Uncensored Power (And Who Doesn't)
Developers building NSFW stories, fantasy worlds, or security research tools need this uncensored LLM. The model answers without refusing controversial or adult topics. It is not for enterprise apps requiring strict brand safety. General purpose chatbots often prefer tame, filtered outputs. If your workflow breaks when the AI refuses a creative prompt, this uncensored AI bot fits. Use it for raw generation, not corporate moderation.
Why This unhinged AI Model Beats Corporate Guardrails
The uncensored LLM delivers raw, unfiltered text output by skipping the polite refusal layer that corporate gatekeepers enforce on every response.
Fantasy Storytelling
Generate dark, violent, or weird narratives without the model softening the edge to suggest dialogue or friendship.
Security Research
Probe edge cases in prompt injection or jailbreak patterns without worrying about content filters blocking lawful adult analysis.
Creative Writing
Write uncensored stories that embrace chaotic plot twists without the API injecting moralizing summaries into your tokens.
Do The Math: Real Cost Examples With Token Arithmetic
Do The Math: Real Cost Examples With Token Arithmetic
Our API charges strictly by token volume, not subscription fees. Input costs $0.15 per million tokens. Output runs $0.50 per million tokens. A 10k input and 1k output request costs just $0.0015 plus $0.0005. You pay only for actual usage. Errors are free. Prepaid credit never expires.
The Uncensored API Buyer's Checklist: 7 Critical Checks
Verify Hard Limits
Check context windows and output caps immediately.
- Confirm 100,000 token context.
- Ensure 16,000 token max output.
- Verify no hidden filtering.
Assess Billing Transparency
Look for prepaid crypto with bonus tiers.
- Start with $0.50 trial.
- No monthly subscriptions.
- Errors cost nothing.
Test Integration Speed
Use standard OpenAI syntax.
- Check base URL format.
- Verify function calling support.
Common Integration Mistakes With Uncensored Models
Developers often assume standard rate limits apply universally without checking specific constraints.
- Misconfigured Output Length: The default max_tokens is 2,048. You must explicitly set this higher, up to 16,000 tokens, or your long context responses will truncate unexpectedly.
- Ignoring Streaming: Sending large payloads without enabling Server-Sent Events creates latency spikes.
- Wrong Model ID: Remember to send
"uncensored" in the model field, not a generic placeholder.Common questions
What is unhinged AI and how does it differ from standard models?
It is a single, uncensored LLM API offering unfiltered responses for adult or creative content. The model refuses only minor age restrictions while allowing diverse topics without corporate bias.
Is the API compatible with existing OpenAI SDKs?
Yes. You can use standard OpenAI-compatible clients by pointing them to our base URL. The syntax remains identical, requiring only a base_url change and your specific API key for integration.
What payment methods are accepted for topping up credit?
We accept only crypto payments: USDT on TRC20 or USDC on Base. Minimum top-ups start at $20, with bonus credits available for larger amounts.
How much context does the model support?
It supports a 100,000 token context window for both prompt and completion. You can generate up to 16,000 tokens per request, or 2,048 tokens if you do not explicitly set the max_tokens parameter.
Are there any monthly subscription fees?
No. We use prepaid crypto billing where you pay only for real token usage. Errors and refusals are free, and your credit never expires as long as you remain an active user.
Can I use this API for function calling and JSON mode?
Yes. The API supports function calling via tools, JSON mode via response_format, and streaming via SSE. It also allows standard parameters like temperature, top_p, stop, seed, and various penalty settings for control.
Retrieve your key instantly
Sign up, grab the key, update the base URL. That is the entire configuration.
