Credits System
Learn how Cencori's prepaid credits system works, including pricing, billing, and cost tracking.
How Credits Work
Cencori uses a prepaid credits system instead of monthly subscriptions. You purchase credits upfront and they're deducted as you use AI models.
1 credit = $1 USD. When you make a request, the cost is calculated and deducted from your organization's balance.
Why Credits?
- No Waste: Only pay for what you use
- No Subscriptions: No monthly fees or commitments
- Predictable Costs: Know exactly what each request costs
- Flexible Budgets: Top up as needed
- Transparent Pricing: See provider cost + markup
Pricing Model
Each request cost = Provider Cost + Cencori Markup
Example Calculation
Request: GPT-4o, 1,000 input tokens, 500 output tokens
Provider Cost (OpenAI):
- Input: 1,000 tokens × $5.00 / 1M = $0.005
- Output: 500 tokens × $15.00 / 1M = $0.0075
- Total Provider: $0.0125
Cencori Markup: 20% = $0.0025
Total Cost: $0.015 (0.015 credits)
Transparency: Your dashboard shows exact provider cost and Cencori markup for every request.
Checking Your Balance
In Dashboard
- Go to your organization dashboard
- Check the credits widget in the header
- View transaction history for details
Via API
Low Balance Alerts
Cencori automatically alerts you when credits run low:
| Threshold | Alert | Action |
|---|---|---|
| $10 remaining | ⚠️ Warning notification | Plan to top up soon |
| $5 remaining | 🚨 Urgent notification | Top up immediately |
| $0 remaining | ❌ Service suspended | Requests blocked until top-up |
Adding Credits
- Go to your organization dashboard
- Click "Add Credits" or "Top Up"
- Choose amount (minimum $10)
- Complete payment via Stripe
- Credits added immediately
Coming Soon: Auto-recharge when balance drops below a threshold.
Cost Tracking
Every request shows detailed cost breakdown:
View aggregated costs in your analytics dashboard:
- Total cost per day/week/month
- Cost by provider
- Cost by model
- Cost by project
- Cost trends over time
Optimizing Costs
Use Cheaper Models
Gemini 2.5 Flash costs ~$0.50/1M tokens vs GPT-4o at ~$15/1M. Use cheaper models for simple tasks.
Set Token Limits
Use maxTokens to prevent unexpectedly long responses.
Cache Responses
For repeated queries, cache responses to avoid redundant API calls.
Monitor Usage
Check analytics regularly to identify expensive patterns and optimize.
Transaction History
View all credit transactions in your dashboard:
- Credit purchases (top-ups)
- Credit usage (requests)
- Refunds (if any)
- Timestamps and descriptions
Export transaction history for accounting:
- CSV export
- PDF invoices
- Date range filtering
Free Tier
Cencori offers a free tier with limited features:
| Feature | Free Tier | Paid Tier |
|---|---|---|
| Available Models | Gemini only | All models |
| Credits | Free (limited) | Pay-as-you-go |
| Analytics | Basic | Full |
| Custom Providers | ❌ | ✅ |