Dashboard Walkthrough
When you log in to TokenSense, you land on the Overview page. This guide explains what you're seeing and where to go next.
KPI cards
Total Spend
Your total AI spend for the selected date range. The delta indicator below shows change vs. the previous period — green means spend went down, red means it went up.
Requests
Total number of AI requests proxied through TokenSense. A sudden spike here often explains a matching spike in spend.
Error Rate
Percentage of requests that returned an error (4xx or 5xx). If this is above 5%, check the Error Codes reference.
Active Workflows
Number of distinct workflows that sent requests in the selected period. Workflows are identified by the x-workflow-tag header.
Spend trend chart
Daily spend over time
The main chart shows your daily AI spend. Use the date range selector in the top right to zoom in (last 7 days) or out (last 90 days). Hover over any bar to see the exact spend for that day.
Action items
Alerts panel
The action items panel shows things that need your attention. Budget warnings appear when a project hits 80% of its budget — click to adjust the cap or review spend. Error spikes appear when a workflow's error rate jumps — click to view the logs and diagnose the issue.
Project filter
Scope the view
Click the project dropdown at the top of the page to filter all data to a single project. This is useful for agencies tracking per-client spend — select the client's project and you see only their data. Select "All Projects" to return to the full view.
Where to go next
Navigate from the sidebar
Costs — detailed per-model cost breakdown.
Workflows — per-workflow spend and request counts.
Logs — raw request log with model, tokens, cost, and latency for every call.
Settings — configure budgets, API keys, provider keys, and team members.