Uncensored API
OpenRouter ai settings keys alternative
Get an uncensored LLM via an openai compatible API with a 100,000 token context window and prepaid crypto billing.
Claim trial keyRead documentation
- $0.15 per 1M input tokens
- 100,000 token context window
- Crypto only top-ups
Test in one request
curl https://api.openrouteraisettingskeys.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Check my current key balance"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.openrouteraisettingskeys.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.openrouteraisettingskeys.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);Core features
OpenAI Compatible
Use standard SDKs with our base URL.
Prepaid Crypto
Pay with USDT or USDC only.
No Monthly Fees
Credit never expires and covers usage.
Streaming Support
Get tokens via SSE with usage data.
Tool Calling
Function calling works with standard JSON.
Privacy First
Prompts are not used for training.
Setup steps
Create Account
Sign up with Google or email.
Get Key
Copy your API key immediately.
Update Config
Point your client to our base URL.
Community use cases
NSFW Creative Writing
Generate adult content without refusals.
Roleplay Sessions
Run long context character interactions.
Data Extraction
Parse text with high accuracy.
Research Analysis
Summarize large documents efficiently.
Switch to uncensored inference in three steps
Update your base URL and API key to connect immediately. First, generate a key via Google or email on the Get API key page. Second, point your client to HTTPS://api.openrouteraisettingskeys.com/v1. Third, set the model id to "uncensored". Your existing OpenAI-compatible code works unchanged. You now access 100k context without subscription fees.
- Generate a key.
- Update base_url.
- Set model to "uncensored".
openrouter AI settings keys: uncensored use cases
The openrouter AI settings keys configuration enables direct, low-friction access to an uncensored LLM for content that ignores standard refusals.
NSFW Creative Writing
Generate adult-themed fiction without content filters blocking mature themes. Send text in, get text out via the standard chat-completions endpoint.
Security Research
Probe model boundaries using the uncensored model to identify edge cases in alignment. Use streaming SSE to monitor token generation in real-time.
Raw Data Ingestion
Pipe large prompts into the 100k context window for unfiltered summarization. Set response_format to json_object for structured outputs.
Provider selection checklist for uncensored inference
Verify the API strictly uses POST /v1/chat/completions and supports streaming via SSE.
- Confirm context window is 100,000 tokens.
- Check if crypto top-ups include bonus credit.
- Ensure no monthly subscription fees apply.
Our uncensored LLM offers 16,000 max output tokens per request. We charge $0.15 per 1M input tokens.
How we differ: 5 concrete signs
We strip away subscription layers, offering a raw, prepaid API where you pay only for tokens used. Our billing is transparent, crypto-native, and has no monthly fees or hidden usage caps. Key management is straightforward: one active key per account replaces the old one instantly. We do not route between vendors; we serve a single uncensored LLM tuned for lawful adult use. Setup is instant via Google or email, with no phone number required.
| Feature | Us | Typical Aggregator |
|---|---|---|
| Billing | Prepaid crypto only | Monthly subscription |
| Keys | One active key | Multiple keys |
| Caps | None | Hidden limits |
What developers actually ask about this topic
How do I configure the API key for uncensored inference? Create a key in Settings, set base_url to HTTPS://api.openrouteraisettingskeys.com/v1, and send model as "uncensored".
- Is it a subscription? No prepaid crypto only.
- Do prompts train my data? No.
- What is the context window? 100k tokens.
- How much does it cost? $0.15 per 1M input tokens.
- Can I use Azure keys? Use our API directly.
- Are refusals charged? No errors are free.
Worked cost examples with token arithmetic
Predictable billing for uncensored LLM usage
You only pay for tokens consumed. Errors and refusals cost nothing.
Consider a prompt of 2,000 input tokens and 500 output tokens. Input cost is $0.0003. Output cost is $0.00025. Total spend is $0.00055. This transparency lets you forecast costs accurately. No hidden monthly fees apply. Credit never expires. You can top up with crypto whenever needed. Use the GET /v1/models endpoint to verify your current balance and usage details instantly.
Frequently asked questions
What is openrouter AI settings keys and how does it relate to uncensored models?
It is a key management system for routing requests. Our uncensored API replaces that layer. You send tokens directly. Errors are free. No subscription exists. Use our endpoint for direct inference without intermediary fees or complex proxy configurations.
Does the uncensored model refuse adult content?
No, it generally does not. The model answers controversial topics. It only blocks minor sexual content. Requests are lawful. Output is direct. You control the context. No hidden filters apply to standard adult fiction or creative writing tasks.
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.
Can I use the official OpenAI SDK with this endpoint?
Yes, it is fully compatible. Change the base URL. Set your API key. Send chat completions. Streaming works via SSE. Function calling is supported. JSON mode is available. Temperature and seed parameters function normally.
What is the maximum context window size?
It supports 100,000 tokens total. Prompt and completion share this. Max output is 16,000 tokens. Default output is 2,048 tokens. You can adjust limits. Requests are fast. Streaming returns usage in the final chunk.
How many requests can I send per minute?
Limit is 300 per minute. Concurrent limit is 8. Body size max is 8 MB. One key per account. Replace key to reset. Usage is transparent. Pay for tokens only. No hidden caps exist.
Generate your key now
Register, copy the token, update the endpoint URL. That is all.
