Chat (OpenAI API reference)
https://platform.openai.com/docs/api-reference/chat
Create (POST)
https://platform.openai.com/docs/api-reference/chat/create
必須
model
messages
オプション
temperature
Defaults to 1
What sampling temperature to use, between 0 and 2.
max_tokens
Defaults to inf
top_p
Defaults to 1
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or temperature but not both.
service_tier
Flex processing
Edit (POST) が存在する！ TODO