• by dstala on 3/8/2023, 5:26:42 PM

    Here's what they mention:

    > Because gpt-3.5-turbo performs at a similar capability to text-davinci-003 but at 10% the price per token, we recommend gpt-3.5-turbo for most use cases.

    Is capability to support trained models only additional advantage of da-vinci-003?