{"version":"2.1.300","anchor":"cache-creation-5m1h-token-split-in-api-telemetry","canonical_anchor":"cache-creation-5m1h-token-split-in-api-telemetry","heading":"Usage records split cache writes by how long the cache lasts","tier":"internal","area":"Prompt Caching","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.300\/e\/cache-creation-5m1h-token-split-in-api-telemetry","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.300","markdown":"### Usage records split cache writes by how long the cache lasts\n\nClaude Code's record of each API request now counts cache-write tokens separately for the 5-minute and 1-hour cache\n\n**What**\n\nThe prompt cache lets Anthropic's API reuse parts of a conversation it has already processed. Writing to it costs tokens, and entries can last 5 minutes or 1 hour.\n\nClaude Code's record of each API request now includes `cache_creation_5m_tokens` and `cache_creation_1h_tokens`. Before, it only had one combined total.\n\n**Why**\n\nIt shows how much cache cost comes from each cache lifetime.\n\n- Area: Prompt Caching\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}