0.5.2: cache tip quotes the session's own model (Flash is 50x, not 30x) - #27
Merged
Merged
Conversation
The cache tip used the card-wide minimum (Pro's 30x). V4.1 Flash, now the default, discounts a hit 50x. cacheDiscountOf(models) reads the models that billed. 0.5.2. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The cache tip told every Flash session that a cached prefix bills at 1/30 of the miss rate. 30x is Pro's discount; V4.1 Flash, now the default, discounts a hit 50x.
cacheDiscountOf(models)takes the smallest discount among the models that actually billed. The rate-table footnote keeps the card-wide floor. README examples now pricedeepseek-flash. 186 tests pass; making the function return the card-wide figure turns them red.🤖 Generated with Claude Code