token_counts

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

Overview

Name	token_counts
Type	Resource
Id	anthropic.messages.token_counts

Fields

The following fields are returned by SELECT queries:

count_tokens

Name	Datatype	Description
input_tokens	integer	The total number of tokens across the provided list of messages, system prompt, and tools.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
count_tokens	select	messages, model	cache_control, output_config, system, thinking, tool_choice, tools	Count the number of tokens in a Message. The Token Count API can be used to count the number of tokens in a Message, including tools, images, and documents, without creating it. Learn more about token counting in our user guide

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
cache_control	string	Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request.
messages	array	Input messages.
model	string	The model that will complete your prompt.
output_config	object
system	string	System prompt.
thinking	object	Configuration for enabling Claude's extended thinking.
tool_choice	object	How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.
tools	array	Definitions of tools that the model may use.

SELECT examples

count_tokens

Count the number of tokens in a Message.

The Token Count API can be used to count the number of tokens in a Message, including tools, images, and documents, without creating it.

Learn more about token counting in our user guide

Query Shape

SELECT
input_tokens
FROM anthropic.messages.token_counts
WHERE messages = '{{ messages }}' -- required
AND model = '{{ model }}' -- required
AND cache_control = '{{ cache_control }}'
AND output_config = '{{ output_config }}'
AND system = '{{ system }}'
AND thinking = '{{ thinking }}'
AND tool_choice = '{{ tool_choice }}'
AND tools = '{{ tools }}'
;

Query Example

SELECT
input_tokens
FROM anthropic.messages.token_counts
WHERE model = 'claude-sonnet-5'
AND messages = '[
  {
    "role": "user",
    "content": "how does stackql work?"
  }
]'
AND system = 'You are a technical assistant. Answer concisely.'
;