token_counts

Creates, updates, deletes, gets or lists a token_counts resource.

Overview

Name	token_counts
Type	Resource
Id	gemini.models.token_counts

Fields

The following fields are returned by SELECT queries:

count_tokens

Name	Datatype	Description
cachedContentTokenCount	integer (int32)	Number of tokens in the cached part of the prompt (the cached content).
▶cacheTokensDetails	array	Output only. List of modalities that were processed in the cached content.
▶promptTokensDetails	array	Output only. List of modalities that were processed in the request input.
totalTokens	integer (int32)	The number of tokens that the `Model` tokenizes the `prompt` into. Always non-negative.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
count_tokens	select	modelsId	generateContentRequest, contents	Runs a model's tokenizer on input Content and returns the token count. Refer to the tokens guide to learn more about tokens.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
modelsId	string
contents	array	Optional. The input given to the model as a prompt. This field is ignored when generate_content_request is set.
generateContentRequest	object	Request to generate a completion from the model.

SELECT examples

count_tokens

Runs a model's tokenizer on input Content and returns the token count. Refer to the tokens guide to learn more about tokens.

Query Shape

SELECT
cacheTokensDetails,
cachedContentTokenCount,
promptTokensDetails,
totalTokens
FROM gemini.models.token_counts
WHERE modelsId = '{{ modelsId }}' -- required
AND generateContentRequest = '{{ generateContentRequest }}'
AND contents = '{{ contents }}'
;

Query Example

SELECT
totalTokens
FROM gemini.models.token_counts
WHERE modelsId = 'gemini-2.5-flash'
AND contents = '[
  {
    "role": "user",
    "parts": [{"text": "how does stackql work?"}]
  }
]'
;