## Overview

The Analytics dashboard provides real-time visibility into your API usage. Track request volume, token consumption, model distribution, and error rates.

## Features

### Request Volume

View your API request count over time with configurable time ranges. Identify usage patterns and peak traffic periods.

### Token Usage

Monitor input and output token consumption across all models. Understand which requests are the most token-intensive.

### Model Breakdown

See a breakdown of requests by model. Understand which models your application uses most and optimize costs accordingly.

### Error Tracking

Track error rates and types (401, 402, 429, 500) to identify authentication issues, credit exhaustion, or rate limiting.

## Using Analytics

### Optimize Model Selection

Use the model breakdown chart to identify expensive models. Consider switching to more cost-effective alternatives for appropriate use cases:

- Replace `claude-opus-4-1` ($15/$75 per 1M tokens) with `claude-sonnet-4-5` ($3/$15) for tasks that don't require maximum capability
- Use `gemini-2.5-flash` ($0.15/$0.60) or `gpt-4o-mini` ($0.15/$0.60) for simple, high-volume tasks

### Monitor Rate Limits

Watch your request volume and implement exponential backoff to avoid `429` errors.

### Track Balance Consumption

Correlate your token usage with balance consumption to predict when you'll need additional prepaid balance.