You'll noticeTier: how much it should matter to you
3Useful: my rating, 1 to 5
0Signal: worth watching, 1 to 5
Prompt CachingArea: what it touches
ImprovementsKind: in v2.1.219,
ImprovementsSection of the release
What
The per-model minimum table was regrouped and a new table lists which top-level request changes can be made without dropping the cache.
Details
Minimums run from 512 tokens for the newest models up to 4096 for Opus 4.6/4.5 and Haiku 4.5, with an explicit note that the value is not monotonic across generations.
The old Amazon Bedrock override is documented as removed.
Cache-preserving forms: tool definitions via tool_addition/tool_removal (beta), and system-prompt content via a role: "system" message with no beta header.
Model switch has no escape hatch.
Mid-conversation system-message availability widens from one model to four, with a caveat that sources conflict on Sonnet.
Evidence
The minimum is not monotonic across generations
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
