{"version":"2.1.295","anchor":"prompt-cache-chain-tracks-model-switches","canonical_anchor":"prompt-cache-chain-tracks-model-switches","heading":"Switching models no longer reuses a stale prompt-cache record","tier":"notice","area":"Prompt Cache","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.295\/e\/prompt-cache-chain-tracks-model-switches","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.295","markdown":"### Switching models no longer reuses a stale prompt-cache record\n\nWhen you switch to a different model mid-conversation, Claude Code now drops the prompt-cache record it was keeping for the old model\n\n**What**\n\nThe prompt cache lets the service reuse work from earlier in a conversation, so repeated parts of a request do not have to be processed again. Claude Code keeps a record that links one request to the next for this purpose.\n\nClaude Code now counts model switches. When you change to a different model, that pending record is set aside or dropped. Before, the record was only released when the chain ended, when the account changed, or when caching was not allowed. A model switch is now a fourth reason. The check also takes into account whether the session was resumed, meaning picked up again after being closed.\n\n**Why**\n\nChanging the model partway through a conversation no longer carries over a cache record that belonged to the previous model.\n\n- Area: Prompt Cache\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}