Usage & Monitoring

Read your own consumption programmatically, per call, or visually — three ways to watch spend.

Read your own consumption back programmatically, per call in every response, or visually in the dashboard — pick whichever fits your workflow.

#Usage endpoints

Endpoint	Returns
`GET /api/v1/usage/charts`	Time-series usage data, shaped for charting.
`GET /api/v1/usage/history`	A paginated list of your usage transactions (filter with `limit`, `startDate`, `endDate`, `type`).
`GET /api/v1/usage/summary`	Aggregated usage statistics (queries, tokens, cost) over a date range.
`GET /api/v1/usage/export`	Your usage transaction history as a downloadable CSV file (`startDate` and `endDate` narrow the range).

curl -s https://api.vedika.io/api/v1/usage/history \
  -H "Authorization: Bearer $VEDIKA_KEY"

#Per-call cost, every response

You do not need to poll anything to know what a call cost. Every AI Query response carries its own cost and credit usage inline, under metadata — see Response Shape for the full field list.

#The dashboard view

For a visual read, the dashboard plots usage and spend over time and breaks it down by endpoint — no integration required. See Cloud Console for what it covers.