# Billing Logs

### Cost Breakdown <a href="#cost-breakdown" id="cost-breakdown"></a>

The [Logs page](https://infron.ai/dashboard/logs) provides users with comprehensive API call history and detailed billing information, enabling you to fully understand the resource consumption and actual costs incurred for each API call.

<figure><img src="https://3822312837-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FZ9C9AjT7j46HAcQrOVWw%2Fuploads%2FqR3CHf08dgYy5wyPyPKS%2Fimage.png?alt=media&#x26;token=0cf65fab-3927-4e87-b071-d1137476d4b7" alt=""><figcaption></figcaption></figure>

Each call record contains the following detailed information:

**Basic Information**

* **Call Time**: Timestamp accurate to milliseconds
* **Request ID**: Unique identifier for issue tracking
* **Model Name**: Specific model version used
* **Call Status**: Status information including success/failure/timeout

**Token Usage Statistics**

* **Input Tokens**: Number of tokens in the input prompt
* **Output Tokens**: Number of tokens generated by the model
* **Total Tokens**: Total token consumption
* **Cached Tokens**: Number of tokens served from cache

**Compute Resource Consumption**

* **Processing Duration**: Actual computation time

**Three-Tier Pricing Display**

To ensure cost transparency, the system provides pricing information across three dimensions:

**1. List Price (Original Price)**

* Cost calculated based on standard official pricing
* Excludes any discounts or promotions
* Serves as the baseline reference for cost calculation

**2. Discounted Price**

* Price after applying account-level discounts
* Includes bulk usage discounts, membership benefits, etc.
* Shows specific discount percentage and savings amount

**3. Cache-Optimized Price**

* Final price after leveraging Prompt Cache technology
* Provides significant cost advantages for repeated or similar requests
* Displays cache hit rate and savings percentage

**Cost Calculation Explanation**

```
Final Cost = (Input Cost + Output Cost) × Discount Factor × Cache Optimization Factor

Where:
- Input Cost = Input Tokens × Model Unit Price
- Output Cost = Output Tokens × Model Unit Price
- Cached portions are calculated at preferential rates
```

### Additional Features

Export & Reporting

* **CSV Export**: Download detailed logs for external analysis
* **Custom Reports**: Generate reports for specific time periods or usage patterns
* **API Integration**: Programmatic access to logs data for automated monitoring

Real-time Monitoring

* **Live Updates**: Real-time refresh of call records
* **Alert System**: Notifications for unusual spending patterns or errors
* **Dashboard Integration**: Quick access to key metrics and trends