Chat with conversational AI that can converse with you, answer follow-up questions, and challenge incorrect assumptions.
OpenAI's GPT (generative pre-trained transformer) models have been trained to understand natural language and code. GPTs provide text outputs in response to their inputs. The inputs to GPTs are also referred to as "prompts". Designing a prompt is essentially how you “program” a GPT model, usually by providing instructions or some examples of how to successfully complete a task.
To use a GPT model via the OpenAI API, you’ll send a request containing the inputs and your API key, and receive a response containing the model’s output. Our latest models, gpt-4 and gpt-3.5-turbo, are accessed through the chat completions API endpoint. Currently, only the older legacy models are available via the completions API endpoint.
gpt-4
gpt-3.5-turbo
Documentation: https://platform.openai.com/docs/guides/gpt/chat-completions-api
ChatGPT_ChatCompletions
Given a list of messages describing a conversation, the model will return a response.
ChatGPT_Completions
Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.
https://en.wikipedia.org/wiki/ChatGPT