Chat completions and completions - the same API or different?

API
1

I found different playgrounds https://platform.openai.com/playground/chat?models=gpt-4o and https://platform.openai.com/playground/complete , however in docs I see them as same API. My final task is to send several messages one by one and finally ask to make one general text from them (this is my approach to go around request token limitation for big models). So the final dialog should look like this (tried it in GPT web version and also here https://platform.openai.com/playground/chat?models=gpt-4o got the same result):

i will send you several messages and then I will ask you to create one general text from them
ChatGPT
Sure, go ahead and send the messages. I'll be ready to create a general text from them once you've sent everything.

User
Once upon a time, lived a frog
ChatGPT
Got it. Please continue with the next messages.

User
She had 5 children
ChatGPT
Okay, noted. Please send the next message when ready.

User
She was very happy

ChatGPT
Understood. Please send the next message.

User
Now join them all in one text
ChatGPT
Once upon a time, there lived a frog. She had 5 children and was very happy.
2

“compete” is for interacting with non-chat base models or the instruction trained gpt-3.5-turbo-instruct model.

Completions takes a prompt input instead of a series of messages.

The gpt-4o model should not be showing in the completions playground. Nor as a model that is automatically added to the API documentation. The playground is not showing you the error message that would occur if you attempt to use it:

Error code: 404 - {'error': {'message': 'This is a chat model and not supported in the v1/completions endpoint. Did you mean to use v1/chat/completions?', 'type': 'invalid_request_error', 'param': 'model', 'code': None}}

If you have a task that requires summation of a series of inputs as data, you should send them all as one message.

The AI will perceive the prior inputs like you show as just a history of what has happened.

If you inserted user and assistant exchanges as past chat history, an input you could provide would be “summarize our chat so far”. The AI will answer that like it was chatting instead of processing text as a task, though.