Models

Model	Description	Training Data
GPT-4	More capable than any GPT-3.5 model, able to do more complex tasks, and optimized for chat.	Up to Sep 2021
GPT-3.5-turbo	Most capable GPT-3.5 model and optimized for chat at 1/10th the cost of text-davinci-003.	Up to Sep 2021
Davinci	Most capable GPT-3 model. Can do any task the other models can do, often with higher quality, longer output and better instruction-following.	Up to Jun 2021
Curie	Very capable, but faster and lower cost than Davinci.	Up to Oct 2019
Babbage	Capable of straightforward tasks, very fast, and lower cost.	Up to Oct 2019
Ada	Capable of very simple tasks, usually the fastest model in the GPT-3 series, and lowest cost.	Up to Oct 2019

Since Turbo and Davinci are the most powerful model, we recommend using them. Turbo is the default model of ChatGPT.