The token-usage schema now records a thinkingTokens field, which is already counted inside outputTokens. This is only populated for turns run on CLI versions that record the field, so it may be partially populated for sessions resumed from older versions.
Names in the bundlethinkingTokens
Documented inclaude-code/agent-sdk/python
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Confirmed since
Anthropic's documentation has since written up thinkingTokens, on Agent SDK reference - Python.
| `thinkingTokens` | `int` | Thinking tokens generated by this model, already counted in `outputTokens`. Absent until a turn runs on a Claude Code version that records it, and not declared on the TypedDict, so read it with `.get()`. Requir…agent-sdk/python see the edit
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agrees
Anthropic's documentation has since written up thinkingTokens, on Agent SDK reference - Python.