●MODEL — Claude Sonnet 5 becomes the default across all plans, with stronger planning, tool use, and autonomy●PRICE — Sonnet 5 launches at $2 input / $10 output per million tokens through August 31●MODEL — Sonnet 5 nears Opus 4.8 performance at a lower price for always-on agents●CODE — Claude Code adopts Sonnet 5 as default with a native 1M-token context window●CODE — Claude Code adds sandbox credential blocking and org-level model restrictions●CLOUD — Claude is generally available in Microsoft Foundry on Azure with Azure-native access●MODEL — Claude Sonnet 5 becomes the default across all plans, with stronger planning, tool use, and autonomy●PRICE — Sonnet 5 launches at $2 input / $10 output per million tokens through August 31●MODEL — Sonnet 5 nears Opus 4.8 performance at a lower price for always-on agents●CODE — Claude Code adopts Sonnet 5 as default with a native 1M-token context window●CODE — Claude Code adds sandbox credential blocking and org-level model restrictions●CLOUD — Claude is generally available in Microsoft Foundry on Azure with Azure-native access

TAG

claude-opus-4-8

1 articles

← Back to all tags

prompt-caching¹ claude-sonnet-5¹ model-migration¹ cost-optimization¹

⬡ API & SDK/2026-07-02Advanced

Your Cache Hit Rate Resets to Zero the Morning You Switch Models — Prompt Cache Rewarm Design for the Opus 4.8 to Sonnet 5 Cutover

Prompt caches are scoped per model, so day one of a model migration starts at a 0% hit rate. Why percentage-based rollouts break cache economics twice over, and how cohort cutover by task family preserves them — with working measurement code.