# 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="/files/hDyAlw7KCMMh86uLaI6S" 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


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://infronai.gitbook.io/docs/observability/billing-logs.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
