/v1/chat/completions endpoint provides full OpenAI API compatibility for text completions, token streaming, and function calling.
Request Parameters
Usage Object Format
Every successful response includes an accurateusage object used for Pay-As-You-Go settlement:
prompt_tokens: Number of tokens in the prompt sent to the model.completion_tokens: Number of billable public tokens generated by the model.total_tokens: Sum of input and output tokens.