Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.guardway.ai/llms.txt

Use this file to discover all available pages before exploring further.

What this is for

Dashboard → Usage aggregates request and token telemetry from every attached gateway into one view. Use it to find which apps drive the most traffic, compare provider/model behavior over time, and inform routing or quota decisions. For cost, see the sibling Spend tab. For guardrail analytics, see Security.

Options

Time range

Same dropdown that drives Overview: Last Hour, Last 24 Hours, Last 7 Days, Last 30 Days.

Filters

  • Gateway — multi-select; leave empty for all.
  • Provider — multi-select.
  • API Key — multi-select.

Breakdowns

BreakdownWhy it’s useful
Per gatewaySpot a noisy environment or a regional imbalance.
Per teamConfirm fairness across business units.
Per API keyFind the application driving volume.
Per providerDecide whether to switch a workload.
Per modelLatency / quality tradeoff analysis.
Each view shows requests, prompt tokens, completion tokens, total tokens, and p50 / p95 latency over the selected time range.

How to configure

This is a read-only analytics view — no configuration on the page itself.
Usage dashboard
1

Open Dashboard → Usage

Open Dashboard → Overview from the dashboard sidebar and click the Usage tab.
2

Pick a window

Set the Time range dropdown.
3

Filter and pivot

Add Gateway, Provider, or API Key filters. Switch the Group by selector between gateway, team, API key, provider, and model.
4

Export

Click Export to download the current filter as CSV or JSON. Useful for showback systems and finance.

What this view does not show

Raw prompts and completions stay on the gateway. To inspect them, open Logs while connected to that gateway. Administrative actions are recorded centrally on the Audit log.
  • Spend — cost view of the same telemetry.
  • Logs — request-level drill-in.
  • Notifications — alert when usage crosses a threshold.