Data Usage
View processed data and retention usage for your project.
Data Usage lets you monitor your project's data consumption across traces, spans, online evaluations, and test runs. Use this page to understand your usage patterns and track progress toward your plan limits.
Overview
The Overview tab provides a breakdown of usage by data type over a selected time period.
Usage Summary
Usage is broken down into five categories:
| Data Type | Description | Billing |
|---|---|---|
| Traces | Top-level observability units representing complete interactions | Contributes to GB usage |
| Spans | Individual operations within traces | Contributes to GB usage |
| Online Evals (metric data) | Evaluations run on production traces, spans, and threads | Counted separately |
| Test Runs | Evaluation runs from experiments and test suites | Counted separately |
| Signals | Classifier runs on traces and idle threads | Counted separately |
The summary shows:
- Total in period — Total data size and unit count for the selected time range
- Average per month — Average monthly data size and unit count
Ingested Trace/Span Data
This section shows your observability data ingestion over time. Your observability data usage is calculated based on GB-months—the total gigabytes of traces and spans ingested over your selected retention period.
You can view the data in three ways:
- Ingested size over time — Total data size ingested per month
- Count over time — Number of traces/spans ingested per month
- Avg size per trace/span — Average size of each trace or span
Online Evals Ran Per Month
This section shows your online evaluation usage over time. Online evals are evaluations run on your production traces and spans in real-time. You'll be charged based on the total number of metric evaluations run beyond your plan's included limits.
The chart displays the number of online evals executed per month, helping you track evaluation volume and identify usage trends.
Signals Ran Per Month
This section shows your classifier usage over time. Each classifier evaluation on a trace or idle thread is counted as one signal run. You'll be charged based on the total number of signals run beyond your plan's included allowance.
The chart displays the number of signals executed per month, scoped to whichever sample rates you've configured for trace and thread classifiers in Project Settings → Classifiers.
Cost Insights
The Cost Insights tab shows how close you are to your plan's included usage limits.
Observability Data Usage
Tracks your trace and span data consumption against your plan's GB-months allowance. The progress bar shows your current usage as a percentage of your included limit, with a breakdown between traces and spans.
Online Evals Usage
Tracks the number of online evaluations run on your production traces, spans, and threads in real-time. Online evals are evaluations that run automatically on incoming observability data, as opposed to test runs which are triggered manually or via CI/CD.
The progress bar shows your current eval count against your plan's included allowance.
Signals Usage
Tracks the number of classifier runs against your project's traces and threads. Each enabled classifier that processes an item counts as one signal run, subject to the configured trace and thread sample rates.
The progress bar shows your current signal count against your plan's included allowance. To control overhead, lower the sample rate on individual classifiers in Project Settings → Classifiers, or disable classifiers you no longer need.
Setting this up for your organization?Set up the controls your team needs before a wider rolloutTalk to usLast updated on