When we talk about GPT-4 today, we mean the GPT-4 Turbo version . OpenAI has released several versions of GPT-4 over the years. OpenAI lists the different versions on the Models website under the menu item "GPT-4 Turbo and GPT-4". The most important GPT-4 versions are discussed here :
GPT-4-0314: This is the first version; it was trained with data up to September 2021 and only has a 4k context window. The small context window makes it virtually impossible to perform longer, connected tasks.
GPT-4-1106-Preview: A preview model that first dataset paved the way for the more powerful and intelligent GPT-4 Turbo.
GPT-4 Turbo Preview: Final preview model, which already has a considerable context window of 128,000 (128k) tokens and is trained with more recent data until December 2023.
GPT-4 Turbo: Final model of GPT-4. This model is built into ChatGPT-4 by default. It has vision functions so that images can be processed as input. Otherwise it is similar to the Turbo Preview model.
The fact that GPT-4 Turbo is now integrated into GPT-4 chatbots as standard has a positive effect on the quality of the chatbots. The context window of 128,000 tokens facilitates the use of the chatbot for longer applications . The reason: An extended context window means that the chatbot can have longer conversations without losing the thread.