Cactus Needle is an interesting model. It's blazingly fast - on my Mini M4 Pro it loads 20 tools toolset and weights in about 1s, very small - 100MB w/ 20 tools, and it runs on the CPU. Quite the fun little toy, indeed.

Cache writes are the vast majority of the "usage" of Fable 5.1 in Claude Code, at over 65% of the cost in my real world usage. The cache read price cut is awesome but cache writes are still way too expensive 🙃

Cache Response Rules are live: control how Cloudflare caches after the origin replies, but before the response is stored. Strip Set-Cookie, rewrite Cache-Control, and set cache tags without touching origin code. Available on all plans now.