Source Intelligence
Follow Discord

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

← All of v0.2.113 Home All releases ←olderv0.2.109 v0.2.114newer→
Claude Code v0.2.113

Token Usage Tracking Enhancements

  • Per-Model Token Tracking: Improved token usage tracking with breakdown by model instead of aggregated totals
  • New display format shows token usage for each model separately
  • Format: Model Name: X input, Y output, Z cache read, W cache write
  • Enhanced Cache Metrics: Better tracking of cache read and cache creation tokens
  • Added functions to separately track cache read input tokens and cache creation input tokens
  • More accurate cache usage reporting in API responses

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

See this entry in the whole of v0.2.113 →