Elarwei aa2826b5b1 fix(usage): parse Kimi K2 cached_tokens from prompt_tokens_details ...

Kimi K2 models use automatic prefix caching and return cache stats in
a nested field: usage.prompt_tokens_details.cached_tokens

This fixes issue #7073 where cacheRead was showing 0 for K2.5 users.

Also adds cached_tokens (top-level) for moonshot-v1 explicit caching API.

Closes #7073

2026-02-24 14:40:52 +00:00

4.5 KiB

Raw Blame History

View Raw