{"version":"2.1.228","anchor":"usage-reports-a-thinking-token-count","canonical_anchor":"usage-reports-a-thinking-token-count","heading":"Usage reports a thinking-token count","tier":"internal","area":"Token Usage","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.228\/e\/usage-reports-a-thinking-token-count","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.228","markdown":"### Usage reports a thinking-token count\n\nToken usage now includes a thinking-token count, accumulated correctly in both streaming and non-streaming modes.\n\n**What**\n\nToken usage now carries an `output_tokens_details` object with a `thinking_tokens` field, parsed from responses and combined correctly across both streaming and non-streaming accumulation.\n\n**Details**\n\n- The zero-usage baseline starts at `{ thinking_tokens: 0 }`.\n- `thinking_tokens` may be null, and placeholder or synthetic usage records set `output_tokens_details` to null.\n\n**Evidence**\n\n`output_tokens_details`\n\n- Area: Token Usage\n- Tier: Under the hood\n- Useful: 3\/5\n- Signal: 3\/5"}