GPT-3.5 is now available with a 16K context window by default and also supports more reliable JSON outputs. The model can be accessed by passing
gpt-3.5-turbo-1106 as the model parameter in the API. Applications using the
gpt-3.5-turbo name will automatically be upgraded to the new model on December 11.
Does GPT-3.5 have an updated knowledge cutoff?
No. The knowledge cutoff has not been updated for this model. It remains September 2021.
How is this model different from GPT-4 and GPT-4 Turbo?
Our GPT-3.5 Turbo series is still faster than GPT-4 and GPT-4 Turbo. While GPT-3.5 is a highly capable model, we recommend using GPT-4 for improved reliability and creativity on higher complexity tasks. Fine-tuning GPT-4 is only available through an experimental program today, whereas GPT-3.5 fine-tuning is generally available.