> ## Documentation Index
> Fetch the complete documentation index at: https://docs.costhawk.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Usage Tracking

> Monitor your AI API costs across all providers

## Overview

CostHawk tracks your AI API usage across multiple providers, giving you a unified view of your spending.

## Supported Providers

* **OpenAI** - GPT-4, GPT-4o, GPT-3.5, Embeddings, DALL-E
* **Anthropic** - Claude Opus, Claude Sonnet, Claude Haiku
* **Google** - Gemini Pro, Gemini Ultra
* **More coming soon**

## Metrics Tracked

| Metric        | Description                              |
| ------------- | ---------------------------------------- |
| API Calls     | Total number of API requests             |
| Input Tokens  | Tokens sent to the model                 |
| Output Tokens | Tokens generated by the model            |
| Cost          | Calculated cost based on current pricing |

## Viewing Usage

### Dashboard

The CostHawk dashboard shows:

* Real-time usage graphs
* Cost trends over time
* Breakdown by provider and model
* Top models by spend

### MCP Server

Ask Claude:

* "What's my usage this month?"
* "Show costs by provider"
* "Which model am I using most?"

## Tagging & Attribution

Add metadata tags to your API calls to track costs by:

* Project
* Environment (dev, staging, prod)
* Team
* Feature
* User

Then query: "Show me costs by project tag"