With Max. Tokens, you determine the text length of the chatbot's response. This is only a guideline for chat models. The model then attempts to generate a text of approximately the desired length.
What are tokens?
Chat models break down text into segments (tokens) to calculate a possible response. The number of tokens generated from a text depends, among other things, on the language in which the model generates text. In English, 1 token is approximately 4-5 characters, or 1 word is approximately 1.5 tokens.
Which settings are useful?
For normal chat conversations, a value of 70-100 tokens for the response is usually sufficient. In role-playing games, it may be useful to increase this number. In most cases, a maximum of 200 tokens is sufficient.
Try different values to find the best setting for your chat scenarios. Keep in mind, however, that the more text generated, the higher the cost.
Set the maximum tokens in the ChatGPT menu:
Set the maximum tokens in the web interface: