Create Chat Completion
POST
/v1/chat/completionsCreate a model response using the OpenAI-compatible Chat Completions format.
Request Body
application/jsonmessages:requiredarrayMessages that make up the conversation.
model:requiredstringModel identifier used for this request.
Allowed
gpt-5.5max_completion_tokens:optionalnumberMaximum number of tokens allowed in the completion.
Example
1024reasoning_effort:optionalstringControls the amount of reasoning performed by supported models.
Allowed
noneminimallowmediumhighxhighmaxExample
mediumtemperature:optionalnumberSampling temperature used to control response randomness.
Response
200A successful request returns a JSON response. The complete example is shown in the code panel.