Agentic Data Plane

Analyze Cost and Usage

The Cost and usage page is the spending and usage report for your Agentic Data Plane: every LLM call the gateway routes is recorded, priced, and charted here. Use it to see where spend comes from, attribute it to a provider, model, agent, user, or tag, and export the numbers for reporting.

After reading this page, you will be able to:

  • Break down spend, requests, and tokens by provider, model, token type, agent, user, or tag

  • Turn on period comparisons and export the data as CSV

  • Identify the agents active right now and open their recent conversations

Prerequisites

This page assumes traffic through at least one LLM provider; with no traffic, the charts are empty.

Dollar values come from per-model pricing: the built-in catalog rates, or the overrides you set on a provider. Cost reporting works without any pricing setup. See Override per-model pricing.

Open the report

Open Cost and usage in the sidebar. The page has two tabs:

  • Cost & usage: The spending report. Charts of spend, requests, and tokens over a time window, with grouping, filters, and CSV export.

  • Activity: The live view. The agents active right now, with a drill-down into their recent conversations.

Choose the time window

The date-range picker offers last 24 hours, last 7 days (the default), last 14 days, last 30 days, last 90 days, month to date, quarter to date, year to date, and custom ranges. The chart subtitle shows the selected date range and bucket size.

When you open the report without a range in the URL, it starts on the default and widens on its own until it finds your most recent spend, one rolling preset at a time, up to last 90 days. The picker always names the range actually in use. Choosing a range yourself, including a custom one, stops the widening for the rest of the visit, and the automatic steps don’t build up browser history. The Activity tab widens its own window the same way.

A custom range sets an exact start and end time, to the minute and interpreted in UTC, rather than a relative period. It writes customStart and customEnd ISO-8601 timestamps to the page URL, so the view is shareable: copy the URL after picking a custom range and any teammate who opens it lands on the same window.

To compare against the period before, turn on the Compare to previous period switch in the date-range picker. The picker shows which previous window the report compares against, and each series in the report compares against its own numbers from that period. While a comparison is on, the picker’s button carries a vs prev badge, and the comparison is recorded in the page URL, so a compared view is as shareable as a custom range.

Hover over a bucket in any chart to read each series' value in that bucket. While a comparison is on, the detail also shows each series' value in the previous period and the change between them, as both an amount and a percentage. A series with no traffic in the previous period reads as (new) rather than a percentage.

Break down and filter

Use Group by to switch the chart breakdown between providers, models, token type, agents, users, and tags:

  • Group by provider to see which upstream consumed the most budget.

  • Group by model to see which model drove spend inside one or more providers.

  • Group by token type to separate input, output, cached, cache-write, and reasoning usage where those buckets apply.

  • Group by agent or user to attribute spend to the agent or the identified caller that drove it.

  • Group by a tag key to attribute spend to a dimension you define, such as department or env. Tag grouping picks the key from a submenu, and the control shows the active key, for example Tag: department. See Track Spend by Tag.

Each dimension, Provider, Model, Cost type, Token type, User, and Agent, has its own filter button above the charts, and you can combine them freely. For example, filter to one Anthropic provider, drill into claude-opus-4-7, then limit the spend view to input tokens. Selecting an agent also narrows the provider options to the providers that agent used. The tag filter is independent of grouping, so you can group by model while filtering to env=prod.

Deleted providers stay in the report so history remains complete. Turn off Show deleted providers to hide them; when everything that matches your filters is from deleted providers, the chart says so instead of rendering blank.

Read the charts

The report includes these charts:

  • Spend over time: Estimated spend in USD for the selected range.

  • Requests over time: Request count for the selected range.

  • Tokens over time: Token count for the selected range.

The chart renders empty buckets in the selected range as zero-height bars rather than gaps, so quiet days line up with their date label and the trend stays readable when traffic is bursty.

The charts share the bucket you’re pointing at. Hovering a bucket in one chart highlights the same time bucket in the other two and shows each one’s detail for it, so spend, requests, and tokens read against the same point in time without hovering each chart in turn.

The chart palette is colorblind-safe. When multiple providers of the same type exist (for example, two OpenAI providers), the chart renders each one with a distinct hatched pattern so the series stay visually distinguishable.

The spend chart footer summarizes the selected view by cost bucket, including total, input, output, cached, cache writes, and reasoning when the selected traffic includes those categories.

Each chart’s legend is interactive. Select a series to hide it, and select it again to bring it back. A hidden series stays in the legend with its label struck through, and the last visible series can’t be hidden, so a chart never empties. Hiding is per chart and per visit. It isn’t recorded in the page URL.

Select a bar to narrow the whole report to the series that bar belongs to. The series' value becomes a page filter on its own dimension, whether that’s a provider, a model, an agent, a user, a cost type, a token type, or a tag value. The result is the same as setting that filter by hand, so the filter buttons show what the drill-down applied, and you clear it there.

When the chart groups by agent, each agent in the legend also has a View activity button. It opens the Activity tab for that agent over the window the chart is showing.

Each chart can be maximized for a closer look, and exported on its own: the chart export downloads the data as currently shown, including any truncation the chart applies to keep the top series readable. The legend, the drill-down, and View activity work the same way in the maximized view.

Download the report as CSV

To export the data behind the charts, use the download controls in the toolbar:

  • Click Download full report to download the complete, untruncated dataset for the current filters and date range as a CSV file. Every cost type and token type is a separate column.

  • Next to Download full report, open the report-grouping options to choose how the exported rows are grouped. Under Time bucket, pick Hourly, Daily, Monthly, or Total (no time column). Under Break down by, select any combination of Provider, Model, User, and Agent.

Use Download full report when you need the whole dataset rather than the charted view.

See which agents are active now

The Activity tab answers a different question from the report: instead of what something cost, it shows what’s running right now. It ranks the agents with traffic over a window of the last hour (the default), the last 24 hours, or the last 7 days, and shows each agent’s change against the previous window. Select an agent to see its recent requests and open a conversation.