PromptTokensDetails¶

class oci.generative_ai_inference.models.PromptTokensDetails(**kwargs)¶

Bases: object

Breakdown of tokens used in the prompt.

Methods

__init__(**kwargs) Initializes a new PromptTokensDetails object with values from keyword arguments.

Attributes

cached_tokens Gets the cached_tokens of this PromptTokensDetails.

__init__(**kwargs)¶

Initializes a new PromptTokensDetails object with values from keyword arguments. The following keyword arguments are supported (corresponding to the getters/setters of this class):

Parameters:	cached_tokens (int) – The value to assign to the cached_tokens property of this PromptTokensDetails.

cached_tokens¶

Gets the cached_tokens of this PromptTokensDetails. Cached tokens present in the prompt.

Returns:	The cached_tokens of this PromptTokensDetails.
Return type:	int