---
title: "GenAI Observability | Grafana Cloud documentation"
description: "Monitor LLM performance, token usage, costs, and user interactions"
---

# GenAI observability

GenAI Observability provides a complete monitoring for Large Language Model (LLM) applications including performance metrics, token usage tracking, cost analysis, and user interaction patterns.

## Overview

The GenAI Observability dashboard is the main monitoring dashboard for LLM applications, offering insights into:

- **Request monitoring** - Volume, success rates, and response times
- **Cost analysis** - Real-time spend tracking and optimization insights
- **Token usage** - Consumption patterns and efficiency metrics
- **Performance analytics** - Model comparisons and trend analysis
- **Error tracking** - Detailed failure analysis and categorization

## Key features

### Performance monitoring

- Request volume and frequency tracking
- Success and failure rate analysis
- Response time distribution and latency monitoring
- Throughput analysis and concurrent request handling

### Cost optimization

- Real-time cost calculation and tracking
- Cost per request analysis and optimization
- Model cost comparison and recommendations
- Budget tracking and cost alert capabilities

### Token analytics

- Input and output token consumption tracking
- Token efficiency analysis and optimization
- Usage pattern identification and trends
- Model-specific token cost analysis

## Getting started

[Setup Guide  
\
Set up GenAI Observability to monitor LLM performance, token usage, and costs](./setup)

[Configuration  
\
Configure advanced GenAI monitoring, alerts, and optimization strategies](./configuration)