Monitor with dashboards

The Monitor page provides custom dashboards that aggregate metrics across logs and experiments in your project. Track request counts, latency, token usage, costs, scores, and custom metrics over time.

​

Filter and group data

Apply filters and groupings at the top of the page to affect all charts. This lets you focus on specific subsets of your data or compare different segments side by side.

​

Create custom charts

Select +Chart to open the chart editor, or select the pencil icon next to any chart title. Measures and filters correspond to SQL options. The “group by” option is a SQL dimension.

​

Time series

Visualize data over time with lines or stacked bars. Time series charts help you spot trends, anomalies, and correlations.

​

Top list

Show values of multiple groups over the entire timeframe. Order by value or alphabetically (ascending or descending).

​

Big number

Display a single aggregate value as one large number. Useful for highlighting key metrics like total requests or average score.

​

Presets

Preset charts are included by default on the Monitor page, covering common metrics like request count, latency, token usage, and scores.

​

Select timeframes

Choose from preset timeframes or click and drag horizontally on time series charts to zoom into a specific period. Double-click to zoom out.

​

View traces

Select any data point on a chart to navigate to the logs or experiments page, filtered to the corresponding time range and series. This lets you quickly investigate specific data points.

​

Create custom dashboards

The default view shows all data for your project. To create a custom dashboard:

1. Add or edit any chart - you’ll be prompted to create a new view before saving
2. Use the dropdown in the top left to duplicate the current view and save as a new dashboard

​

Unit types

Charts display values with appropriate unit formatting:

• Duration: Seconds (e.g., “1.5s”, “0.3s”)
• Cost: US dollars (e.g., “$0.05", "$1.23”)
• Percent: Percentages (e.g., “75%”, “100%”)
• Bytes: Binary byte units using base-1024 (e.g., “1 KB”, “2 GB”, “500 B”)
• Count: Generic countable things (e.g., “1,234”, “5.5”)

The unit type affects how values appear in chart axes, tooltips, and legends.

​

Next steps

• Use the Loop to ask questions about your data
• Score online to add quality metrics to dashboards
• Build datasets from patterns you identify
• Read the SQL reference for advanced queries