OpenAI Compatible
Drop it into any existing client with a simple base_url swap.
Raw API Access
Set It Uncensored API
Get your uncensored AI API key now with a 100k token context window and pay only for the tokens you actually use.
- OpenAI-compatible endpoints.
- Crypto only payments.
- 100k token context.
Test with one call
curl https://api.setituncensored.com/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.setituncensored.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.setituncensored.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);- $0.15
- per 1M input tokens
- $0.50
- Output tokens / 1M
- 100,000
- token context
- $0.50
- trial credit
- 300
- requests per minute
Core capabilities
No Training Data
Your prompts stay yours and are never used to train the model.
Streaming Support
Receive real-time tokens via SSE with usage stats in the last chunk.
JSON Mode
Force structured outputs easily using the standard response_format parameter.
Function Calling
Define tools and let the model decide how to execute them.
No Subscription
Pay per token with prepaid credit that never expires.
Setup guide
Create Account
Sign up with Google or email to get your key instantly.
Add Crypto
Top up your balance with USDT or USDC to start using the API.
Send Request
Point your SDK to the base URL and send your first prompt.
Community projects
Content Generation
Write long-form articles without hitting sudden content refusal walls.
Roleplay Apps
Build characters that stay in context and answer naturally.
Data Extraction
Parse documents with high accuracy using JSON mode responses.
Research Tools
Analyze controversial topics without standard model bias or filtering.
Why Set It Uncensored Wins
Set It Uncensored wins because we provide raw, open-weight model responses without content refusals for lawful adult use. Your prompts stay yours.
Direct & Transparent
We sell one uncensored LLM API. No subscription fluff. Pay only for tokens you actually use.
Developer First
Get streaming via SSE and function calling. Change your base URL in seconds.
No Training
Your data isn't used for training. Keep your context private and secure.
Swap Your Base URL in 3 Steps
Change your base URL to HTTPS://api.setituncensored.com/v1 and update your API key. Our API is fully OpenAI-compatible, so no code changes are required. Your prompts stay yours, and you get direct access to an uncensored LLM without the usual content filters. Simply swap the endpoint, keep your existing SDK, and start generating unrestricted text immediately. No subscription fluff, just raw performance.
From Signup to First Token
- Sign up with Google or email to receive your API key instantly. No phone number required.
- Add crypto credit via USDT (TRC20) or USDC (Base). Minimum top-up is $20.
- Point your client to HTTPS://api.setituncensored.com/v1 with model id
uncensored. - Send a request. You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens.
Uncensored vs. The Rest
Our API strips away the fluff, offering raw, uncensored text generation via a single open-weight model.
Built for Coders, Writers, and Creators
Built for Coders, Writers, and Creators
Our API serves developers who need raw text without standard refusals.
- Coders integrate the uncensored LLM API via simple OpenAI-compatible SDKs.
- Writers generate unrestricted fiction for adult or controversial topics.
- Creators produce diverse content without hidden filters.
It is not for teams needing image generation or fine-tuning.
Stop Making These Uncensored AI Mistakes
Most users waste credits by ignoring context limits. Our model handles 100,000 tokens, yet many send massive payloads without adjusting max_tokens, causing expensive, truncated responses. Always set explicit output caps. Also, avoid assuming unlimited concurrency; we enforce eight simultaneous requests per key. Respect the 300 requests per minute limit to prevent throttling. These simple adjustments ensure you pay only for what you actually use, keeping your uncensored AI API experience efficient and cost-effective.
Common questions
What is set it uncensored?
It is a hosted, OpenAI-compatible API endpoint serving one uncensored large language model. You get direct text access without content refusals for lawful adult use. The service runs on bare-metal infrastructure.
Does it support function calling?
Yes. The API supports function calling, JSON mode, and streaming via SSE. You can configure parameters like temperature, top_p, and stop sequences. It handles tool_choice and response_format objects.
How much does it cost per token?
Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. Errors and refusals are free. You only pay for actual token usage with prepaid credit that never expires.
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.
What is the maximum context window?
The context window is 100,000 tokens. This total includes both the prompt and the completion. Your maximum output per request is 16,000 tokens unless you specify a different limit.
Are my prompts used for training?
No. Prompts are not used for training your data. The model does not refuse lawful adult or controversial topics. Only sexual content involving minors is strictly refused.
Get your API key in seconds
Sign up, grab your key, update your base URL. That is all there is to it.
