Builder

Detailed breakdown of cache writes by TTL. Empty if no cache creation occurred. Sorted by TTL duration (1h before 5m).

The number of input tokens read from the cache for the request.

The number of input tokens written to the cache for the request.

The number of tokens sent in the request to the model.

The number of tokens that the model generated for the request.

The total of input tokens and tokens generated by the model.