{"version":"2.1.221","anchor":"usage-stats-now-count-and-show-cache-tokens","canonical_anchor":"usage-stats-now-count-and-show-cache-tokens","heading":"Usage stats now count and show cache tokens","tier":"notice","area":"Usage & Limits","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.221\/e\/usage-stats-now-count-and-show-cache-tokens","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.221","markdown":"### Usage stats now count and show cache tokens\n\nUsage stats now count cache tokens and show a read\/write breakdown per model.\n\n**What**\n\nToken totals on the stats screens include cache traffic, which changes the headline number, the favorite-model ordering and each model's share percentage.\n\n**Details**\n\n- The per-model scoring helper now sums `inputTokens`, `outputTokens`, `cacheReadInputTokens` and `cacheCreationInputTokens`; previously it was input plus output only.\n- A breakdown line is appended to the text summary in the form `Input \u2026 \u00b7 Output \u2026 \u00b7 Cache read \u2026 \u00b7 Cache write \u2026`, assembled at runtime from fixed fragments.\n- Each of the top three models gains a second dim line built from the fragments `Cache: `, ` read \\xB7 ` and ` write`.\n- Neither the summary line nor the per-model line exists in 2.1.220.\n\n**Evidence**\n\n`Cache read ${od(n)} \\xB7 Cache write ${od(o)}`\n\n- Area: Usage & Limits\n- Names: `\/usage`\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 0\/5"}