generative-ai-python

google.generativeai.protos.CountTokensResponse

View source on GitHub

A response from CountTokens.

It returns the model’s token_count for the prompt.

Attributes
`total_tokens`	`int` The number of tokens that the ``Model`` tokenizes the ``prompt`` into. Always non-negative.
`cached_content_token_count`	`int` Number of tokens in the cached part of the prompt (the cached content).

This site is open source. Improve this page.