Skip to main content

Set cut-off limit

Set a cut-off limit for the responses of the GPT functions in the current spreadsheet. This won't shape the response, but if the response goes beyond this limit, it will be truncated.

TermDefinition
TokenTokens can be thought of as pieces of words. During processing, the language model breaks down both the input (prompt) and the output (result) texts into smaller units called tokens. Tokens generally correspond to ~4 characters of common English text. So 100 tokens are approximately worth 75 words. See how text is split into tokens.
Context windowTotal amount of tokens that the model can consider at one time, including input (prompt) and output (result). The context window size depends on the model used.
Max outputMaximum number of tokens that can be generated in the output by a given model. Max output is typically much lower than Context window.
Cut-off limitMaximum size of the result in GPT for Sheets, measured in tokens. If the result is larger than this limit, it will be truncated. Helps control cost and speed. Cut-off limit is set 200 tokens below Max output.
Prerequisites
You have opened a Google spreadsheet and selected Extensions > GPT for Sheets and Docs > Open.

  1. In the GPT for Sheets sidebar, click Settings from the GPT functions tab.

  2. Set Cut-off limit as follows:

    • Auto: The model automatically uses the maximum number of tokens allowed by the model for responses (with Safe mode only).
    • Fixed: The maximum number of tokens is set manually using the slider (without Safe mode, only the slider is shown).
      • If you expect short responses, lower the limit to get faster responses
      • If you expect long responses, increase the limit to make sure they are not truncated
      • If your response is truncated, increase the limit

        Use the slider or the Auto option so set a cut-off limit

Existing formulas will not automatically update to the new cut-off limit if the cache is enabled. To re-execute them with a new cut-off limit, you can either disable the cache, select the formulas and regenerate their results, or change a parameter in the formulas and press Enter.

What's next

Change other settings to customize how the language model operates.