How Billing Works
Everything you need to know about how you're charged and how to manage your account.
NagaAI operates on a Pay-As-You-Go (PAYG) billing model, ensuring you only pay for what you use. Our transparent pricing structure is designed to scale with your needs, from small experiments to enterprise deployments.
Billing Overview
Our concept is simple:
No plans, no tricks, no nonsense. You're charged based on actual usage — nothing more, nothing less.
Our billing system charges you based on the number of tokens processed by each model after each request. Different models have different pricing based on their capabilities and computational requirements.
Token-Based Pricing
What Are Tokens?
Tokens are the fundamental units of data processing in AI models. They represent pieces of data that can be:
- Words or parts of words (e.g., "hello" might be one token, "unhappiness" might be two)
- Special characters (punctuation, symbols)
- Images (visual data broken into token representations)
- Audio speech (sound data encoded as tokens)
- And more...
Rule of thumb: On average, 1 token ≈ 4 characters or ≈ 0.75 words in English. A typical sentence contains 15-20 tokens.
Input vs Output Tokens
Our pricing distinguishes between two types of tokens:
| Token Type | Description | Cost | 
|---|---|---|
| Input Tokens | Content you send to the model (prompts, images, audio) | Lower cost | 
| Output Tokens | Content generated by the model (responses, images, audio, etc.) | Higher cost | 
Why do output tokens cost more?
Output tokens typically cost more because:
- Generation requires significantly more computational resources
- Each output token depends on processing all previous tokens
- The model must maintain context and coherence throughout generation
Pricing Structure
Example: Claude Sonnet 4.5
Let's break down the pricing for our popular claude-sonnet-4.5 model:
{
  "model": "claude-sonnet-4.5-20250929",
  "pricing": {
    "per_input_token": 0.0000015,
    "per_output_token": 0.0000075
  }
}
Cost Calculation Example
Here's how costs are calculated for a typical interaction:
Your prompt:
Hello! Can you help me?
- Input tokens: ~14 tokens
- Cost: 14 × $0.0000015 = $0.000021
Model response:
Hello! I'd be happy to help you. What do you need assistance with today?
- Output tokens: ~21 tokens
- Cost: 21 × $0.0000075 = $0.0001575
Total Cost
$0.000021 + $0.0001575 = $0.0001785
This example interaction costs approximately 56 times less than 1 cent!
Viewing Current Pricing
You can always check the latest pricing for all available models:
- Website: https://naga.ac/models
- API: https://api.naga.ac/v1/models
Payment Methods
We accept the following payment methods for maximum flexibility:
| Payment Method | Description | 
|---|---|
| Credit Cards | Visa, Mastercard, American Express, etc. | 
| Revolut | Fast and secure payments via Revolut | 
| PayPal | Worldwide payment processing | 
| Cryptocurrency | 300+ coins including USDC, TON, DOGE, and hundreds of others! | 
We support a wide range of cryptocurrencies for maximum payment flexibility. Your preferred coin is likely supported!
Managing Your Balance
Checking Your Balance
Monitor your account balance and usage at any time through the NagaAI Dashboard.
The dashboard provides:
- Current balance
- Recent transaction history
- Detailed usage metrics per model
- Spending analytics and trends
Topping Up
You can add funds to your account at any time:
- Navigate to the Billing Dashboard
- Click "Top Up Balance"
- Enter the amount
- Choose your payment method
- Complete the payment
Your balance is updated instantly and ready to use.
Frequently Asked Questions
What happens if I use all my balance?
Your access to our models will be temporarily suspended due to insufficient credits for processing. To restore access, simply top up your balance through the dashboard. Your API keys remain valid, and service resumes immediately after payment.
Do my credits expire?
No! Your credits never expire. Pay once, use whenever you need — no time pressure, no monthly renewals.
Can I get a refund?
Refunds are handled on a case-by-case basis. If you have concerns about charges or need assistance, please reach out to our support team on our Discord server.
Are there any hidden fees?
No. We believe in complete transparency. You only pay for the tokens you use — no processing fees, no monthly minimums, no hidden charges.