CATCH #871
DETECTED AUG 20, 2026 19:18 UTC
THE CATCHscore 7/10
EXHIBIT 871 · URGENT
Aug 20, 2026 19:18 UTC
web app
https://platform.claude.com
Anthropic's Claude platform console deployed new strings hinting at a breakdown of output tokens, specifically for internal reasoning vs. actual response.
READY TO POST:
looks like claude is adding more granular token breakdowns in their console, showing internal reasoning vs. what's actually returned. could be useful for cost analysis!
anthropic's platform console update suggests new output token categories, especially for 'internal reasoning' tokens. more transparency for developers.
EVIDENCE — the receipts
⚠️ FROM WEB-APP BUNDLE — may include vendored-dependency strings, verify before posting.
Anthropic Console (https://platform.claude.com) deployed new frontend code [4e0731ce8c425a51 -> c269b7ec60e77c6c]: +142 strings, -510 strings, 2 interesting
[feature_flag] (2)
+ Breakdown of output tokens by category.
`output_tokens` remains the inclusive, authoritative total used for billing.
This object provides a read-only decomposition for observability — for example,
how many of the billed output tokens were spent on internal reasoning that may
have been summarized be
+ Number of output tokens the model generated as internal reasoning, including
the thinking-block delimiter tokens.
Reflects the raw reasoning the model produced, not the (possibly shorter)
summarized thinking text returned in the response body. Computed by
re-tokenizing the raw reasoning text, so it
caught by the 20-minute sweep ·
the live wire · all receipts