See what makes up a trace’s token usage and cost
Inspect input, output and cache usage alongside the cost of a trace or individual span.
Xinwei He
Hover over a trace or span’s token and cost totals to see what makes them up.
Token details separate input, output, cache reads and writes, and reasoning tokens when reported. Cost details show the dollar amounts for uncached input, cache reads, cache writes and output.
The same breakdown is available for an individual model call and the trace total, making it easier to see where spending comes from. See cost tracking for how token usage and model pricing determine those amounts.