fix(ai): price anthropic 1h cache writes at 2x input#5738
Merged
mitsuhiko merged 2 commits intoJun 15, 2026
Conversation
anthropic 1h cache writes were billed at the 5m rate; split the bucket and price the 1h portion correctly - add optional `Usage.cacheWrite1h` for the 1h-retention subset of `cacheWrite` - read `cache_creation.ephemeral_1h_input_tokens` from the anthropic `message_start` usage - in `calculateCost`, charge 1h writes at 2x base input and the rest at the existing 5m `cacheWrite` price - cover the split and the no-breakdown fallback with an sse-driven test on `claude-opus-4-8`
Member
|
Thank you! |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
refs #5737
pi prices every anthropic cache write at the 5m rate because the provider reads the aggregate
cache_creation_input_tokensand drops the 5m/1h split, so 1h writes undercount by 1.6x. this readsephemeral_1h_input_tokensand charges the 1h slice at 2x base input incalculateCost.tested: sse-driven test on opus 4.8, a 600k/400k split lands at 7.75 (was 6.25), no-breakdown falls back to 6.25.
npm run checkand ai tests pass.