Create Chat Completion
POST
/v1/chat/completionsCreate a model response using the OpenAI-compatible Chat Completions format.
Request Body
application/jsonmessages:requiredobjectMessages that make up the conversation.
Example
[{"role":"developer","content":"You are a helpful assistant."},{"role":"user","content":"Hello!"}]model:requiredstringModel identifier used for this request.
Allowed
gpt-5.5Example
gpt-5.5max_completion_tokens:requirednumberMaximum number of tokens allowed in the completion.
Allowed
1024reasoning_effort:requiredstringControls the amount of reasoning performed by supported models.
Allowed
noneminimallowmediumhighxhighmaxExample
mediumtemperature:requirednumberSampling temperature used to control response randomness.
Response
200A successful request returns a JSON response. The complete example is shown in the code panel.
Compatibility References
Use these external references to review additional parameters supported by compatible provider formats.