The models used by the API are as follows:

  • gpt-4
  • gpt-4-32k
  • gpt-4-1106-preview
  • gpt-3.5-turbo
  • gpt-3.5-turbo-16k

It is important to note that each model has a different token treatment. If you want to determine how many tokens the completion request uses, refer to the documentation.

We recommend visiting the official information for each model to calculate the tokens used in agent responses.