Ask a question to get started
Enter to send•Shift+Enter new line
total_token_details: Optional[Dict[str, int]] = None
total_token_details sums per-category token counts across traces in the thread.
total_token_details
Keys are model-specific category names (for example cache_read, cache_write, reasoning, audio).
cache_read
cache_write
reasoning
audio
Example: {"cache_read": 400, "reasoning": 120}.
{"cache_read": 400, "reasoning": 120}
