Follow Discord
Sweep 03 Nov 2026 · 22:27Z Build v2.1.318 536 read Stable v2.1.311 Latest v2.1.318 Next v2.1.318 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.317 ·

Per-model prompt caching switches now match other names for the same model

The DISABLE_PROMPT_CACHING_* variables now also turn caching off for aliases and variants of their model, not only an exact name match

You'll notice Bug Fixes
JSON All of v2.1.317
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
Prompt CacheArea: what it touches
Bug FixesKind: in v2.1.317,
Bug FixesSection of the release
What

Prompt caching lets the service reuse parts of a prompt it has already processed, which saves time and cost. Each of these environment variables (settings you set in your shell before starting Claude Code) turns it off for one model:

Before, each one only applied when the model name matched exactly. Now each one also applies to aliases and variants of the same model.

Why

If you set one of these and use the model under a short alias or a variant name, caching is now turned off for it too, where before it could stay on.

How sure we are
One source agreesOne thing we can check says the same as this entry.
Anthropic's release notes agreeFixed DISABLE_PROMPT_CACHING_OPUS and DISABLE_PROMPT_CACHING_SONNET having no effect on [1m], other-region and undated spellings of the…

See this entry in the whole of v2.1.317 →

Feedback