InputTokenCount

The InputTokenCount() function returns the number of input tokens that have been sent to the AI model for an AI agent conversation. Input tokens cover everything the model receives, such as the agent instructions, the conversation history and the user's prompt.

Use this function together with OutputTokenCount() for cost tracking, usage quotas, or to display token usage in the application.

This function is NOT SQL compatible. For more information about SQL compatibility, see our documentation.

Returns a numeric value containing the number of input tokens used by the conversation.

Syntax

InputTokenCount(conversation)

InputTokenCount([Client.Conversation]) => 1284

Parameters

Name	Type	Required	Description
conversation	AI agent conversation	☑️	an AI agent conversation field from the data model