Uncensored LLM API
Unrestricted ai API for developers
Drop our unrestricted AI model into your stack today with a 100,000 token context window and simple OpenAI compatible endpoints ready for your bot.
- $0.15 per 1M input tokens
- 100,000 token context window
- Crypto top-ups only
curl https://api.aiunrestricted.cc/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "What is the capital of France"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.aiunrestricted.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.aiunrestricted.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);- per 1M input tokens
- $0.15
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
Core features
OpenAI Compatible
Use standard SDKs with our base_url and model id.
Uncensored Model
Answer without refusals for lawful adult and creative content.
Streaming Support
Get tokens via SSE with usage data in the last chunk.
Function Calling
Execute tools and enforce JSON mode with built-in parameters.
No Subscription
Prepaid credit charges by usage with no monthly fees ever.
Fast Integration
Start generating text with a single API key change.
Setup guide
Get Your Key
Sign up with Google or email to receive your key instantly.
Add Crypto Credit
Top up with USDT or USDC to start sending requests.
Send Requests
Point your client to our base_url and start generating text.
Community projects
NSFW Chatbots
Build unrestricted character bots for Telegram or web platforms.
Creative Writing
Generate stories without content filters blocking your narrative flow.
Coding Assistants
Get code outputs without refusals for technical or mature topics.
Roleplay Clients
Create immersive experiences with a model that never breaks character.
From signup to first token: your 3-step integration
Start generating unrestricted content in under two minutes.
- Sign up via Google or email on the Get API key page to receive your credentials instantly.
- Update your SDK client with the provided base URL and API key.
- Send a POST request to /v1/chat/completions using the model id "uncensored".
You will receive streaming tokens immediately.
Why this isn't just another proxy: 5 concrete signs
We deliver one uncensored model via a standard chat-completions endpoint. Unlike aggregators mixing vendors, our API never routes your requests elsewhere. You get consistent, low-latency inference optimized for unrestricted content without enterprise bloat. Our single, truly uncensored model integrates instantly with standard OpenAI SDKs. There is zero model-routing complexity, ensuring you always get the same reliable behavior for your NSFW-tolerant clients.
| Feature | Us | Typical Proxy |
|---|---|---|
| Models | One | Many |
| Routing | None | Dynamic |
Use cases for unrestricted AI: roleplay, writing, and coding
Unrestricted AI powers diverse projects by removing content filters that break immersion or block technical nuance.
Roleplay and Character Bots
Build NSFW chatbot experiences without sudden refusals. The model handles complex personas and adult themes directly.
Creative Writing
Generate uncensored stories with full narrative freedom. Avoid tone-policing for dark or mature themes.
Developer Tools
Use uncensored coding AI to extract code without formatting restrictions. The 100k context window supports large codebases.
Content Generation
Create unrestricted AI generator outputs for adult content. Send text in, get text out with zero blocking.
Real token arithmetic: how much will your project cost?
Costs depend strictly on input and output volume. Our pricing is $0.15 per 1M input tokens, plus $0.50 per 1M output tokens. Streaming ensures you only pay for delivered content. A 10k prompt with 2k output costs roughly $0.0015. Errors are free. Credit never expires. Top up via crypto starting at $20. Track usage via the dashboard to keep your bot running without surprise charges.
The uncensored provider checklist: 7 questions to ask
7 questions to ask
- Does the API key work instantly via Google or email, without requiring a phone number?
- Is pricing strictly $0.15 per 1M input tokens and $0.50 per 1M output tokens, with no hidden monthly fees?
- Do you accept only USDT (TRC20) or USDC (Base) for top-ups, and do you offer bonus credit on larger deposits?
- Is the model truly uncensored, refusing only specific unlawful content like minors?
- Does the provider support standard OpenAI parameters like temperature, top_p, and streaming via SSE?
- Are prompts kept private and not used for training your data?
- Is there a clear, no-nonsense refund policy for unused credits that never expire?
Common integration mistakes and how to avoid them
Developers often misconfigure base URLs or ignore context limits, causing silent failures. Set your base URL to HTTPS://api.aiunrestricted.cc/v1 and send the model ID "uncensored" exactly. Always specify max_tokens to avoid defaulting to 2,048 output tokens. Since our API supports 100,000 tokens, passing the full context in one request ensures consistency. Streaming via SSE handles token usage efficiently. Check your key limits: 300 requests per minute per key.
Common questions
What is unrestricted AI and how does it differ from standard models?
Unrestricted AI refers to our single uncensored model that does not refuse lawful adult or controversial topics. It accepts text input and returns text output via the standard chat-completions endpoint, ensuring consistent behavior without routing complexity or external model mixing.
Does this API support streaming responses for real-time applications?
Yes, streaming is fully supported via Server-Sent Events (SSE). You receive individual tokens as they are generated, with the final chunk containing the complete token usage statistics for accurate billing and tracking within your client application.
Can I use this service for NSFW chatbot development?
Yes, the model is explicitly tuned to answer without content refusals for lawful adult use. It handles NSFW chatbot scenarios effectively, provided the content does not involve sexual content involving minors, which remains a hard limit for all requests.
What is the context window size for this LLM?
The context window supports 100,000 tokens for the combined prompt and completion. You can request up to 16,000 output tokens per request, or default to 2,048 tokens if you do not explicitly set the max_tokens parameter in your call.
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.
Is the trial credit valid indefinitely after signup?
No, the $0.50 trial credit is valid for only 7 days.
