Uncensored Model
Generate text without content refusals for lawful adult use.
Drop-in API
LLM api router for uncensored generation
Integrate an uncensored LLM with a 100,000 token context window. Change your base URL and API key, then generate text instantly using our openai compatible API.
Claim trial keyView documentation
100,000 token context window
No monthly subscription fees
Zero configuration required
Test with a single call
curl https://api.llmapirouter.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "list all npm packages"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.llmapirouter.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.llmapirouter.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);- $0.15per 1M input tokens
- $0.50Output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
Core features
OpenAI Compatible
Works with existing SDKs by changing your base URL.
Streaming Support
Receive tokens via SSE with usage data in the final chunk.
JSON Mode
Force structured outputs using the response_format json_object parameter.
Function Calling
Support for tools and tool_choice in chat completions.
Privacy First
Prompts are not used for training your model data.
Setup process
Get Your Key
Sign up with Google or email to receive your API key instantly.
Update Endpoint
Change your client base_url to HTTPS://api.llmapirouter.com/v1.
Send Request
Post to /v1/chat/completions with model id uncensored and start generating.
Common use cases
Content Generation
Create stories or articles without artificial content filters blocking creative topics.
Data Extraction
Parse complex text using JSON mode for reliable structured output delivery.
Code Completion
Generate code snippets with full context window support for long files.
Research Analysis
Process large documents within the 100,000 token limit for deep analysis.
Worked cost examples with token arithmetic that use only our prices
Your total cost equals the sum of input and output token charges. For a 100,000 token prompt plus 16,000 token completion, you pay exactly $0.023. We charge $0.15 per million input tokens and $0.50 per million output tokens. Errors consume no credit. This transparent pricing ensures you never pay for refusals.
LLM API router: the uncensored drop-in alternative
The LLM API router provides an open-weight model that answers without refusals for lawful adult use.
Drop-in Integration
Change base_url and key. Existing code works immediately with zero configuration.
Generous Context
Support 100,000 tokens. Complex prompts stay intact without truncation.
Streaming Support
Receive token usage in the last chunk. Debug efficiently with SSE.
JSON Mode
Force structured outputs. Parse responses reliably for automation.
How this differs from a typical alternative on 4-6 concrete signs
6 concrete differences
| Feature | Typical alternative | Ours |
|---|---|---|
| Pricing | Complex tiers | $0.15 input, $0.50 output per 1M tokens |
| Payments | Cards, invoices | Crypto only (USDT, USDC) |
| Key limits | Multiple keys | One key per account |
| Routing | Multi-model | Single uncensored model |
| Subscriptions | Monthly fees | Prepaid credit only |
| Expiration | Timed credits | Never expires |
A checklist for choosing a provider in this niche
Verify token pricing transparency before committing. Check if errors incur charges or remain free. Confirm the context window supports your data volume. Ensure the API key limits allow your concurrency needs. Look for crypto-only top-ups if you prefer privacy. Avoid providers that route to unknown models without disclosure. Our service offers $0.15 per million input tokens with no hidden fees.
Move to uncensored generation in three steps
Switch your provider by updating two configuration values. First, replace your current base URL with HTTPS://api.llmapirouter.com/v1. Second, insert your new API key into your client settings. Third, change the model identifier to "uncensored". Your existing code works immediately with zero configuration. You can now generate content without content filtering. Use our official OpenAI SDKs to integrate in minutes.
Common mistakes people make in this niche and how to avoid them
Developers often assume uncensored implies unrestricted speed or infinite context. This API enforces a hard 100,000-token limit and caps output at 16,000 tokens per request. Many also confuse this service with complex multi-model routers; we serve a single uncensored model via a strict OpenAI-compatible endpoint. Always verify your base_url and ensure your client handles streaming SSE correctly. Avoid hidden costs by monitoring token usage, as errors remain free but valid requests incur charges.
Frequently asked questions
What is the LLM API router pricing structure?
It charges $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals cost nothing. Prepaid credit never expires, so you only pay for actual usage without monthly fees.
Can I use the official OpenAI SDK?
Yes, the API is fully OpenAI compatible. Simply update your base_url to HTTPS://api.llmapirouter.com/v1 and set your API key. Your existing code works immediately without changes to function calls or parameters.
What is the context window limit?
The model supports a 100,000-token context window for both prompt and completion combined. The maximum output per request is 16,000 tokens, or 2,048 tokens if you do not specify max_tokens.
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 model used for training my data?
No, prompts are not used for training. An account requires only an email address. Your data privacy is preserved without requiring phone numbers or complex verification steps during the signup process.
What happens if I make an error?
Errors and refusals are free. If you experience a double charge, you can fix it through the Support page. Credit is not refunded but never expires, ensuring you keep your balance for future requests.
Unlock your API key
Register, copy the token, and update your base URL. Setup takes seconds.
