{"version":"2.1.296","anchor":"pricing-tier-id-for-a-1m-context-model-changed","canonical_anchor":"pricing-tier-id-for-a-1m-context-model-changed","heading":"A 1M-context model moves to a pricing tier with its own cache-read rate","tier":"internal","area":"Models","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.296\/e\/pricing-tier-id-for-a-1m-context-model-changed","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.296","markdown":"### A 1M-context model moves to a pricing tier with its own cache-read rate\n\nA model with a 1M-token context window and 128000 output tokens now uses a pricing tier that sets a separate cache-read rate\n\n**Unclear.** Which model this pricing change applies to is not named.\n\n**What**\n\nOne model in Claude Code's model list, the one with a 1-million-token context window and up to 128000 output tokens, now uses a different pricing tier. The new tier, `tier_2_10_cache_read_0_10`, names its own rate for cache reads. A cache read happens when the model reuses text it has already processed. The old tier was `tier_2_10`.\n\n**Why**\n\nThe cost Claude Code shows for this model can change, especially in sessions that reuse a lot of cached text.\n\n- Area: Models\n- Tier: Under the hood\n- Useful: 3\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: no"}