QuestionQ22Verified/Use GenAI and LLM capabilities in SnowflakeCopy linkReport a problemAsk AstroTutorSave questionFor which Snowflake Cortex LLM functions are both input and output tokens counted?Choose threeASUMMARIZEBSENTIMENTCTRANSLATEDEMBED_TEXT_768EEMBED_TEXT_1024FCLASSIFY_TEXTShow AnswerAnswerExplanationSnowflake counts both input and output tokens for text-generating Cortex functions. SUMMARIZE and TRANSLATE generate text responses, and CLASSIFY_TEXT generates a classification response, so each incurs input- and output-token usage. Embedding functions count only input tokens, while sentiment analysis is not included among the functions billed for both.Learn moreCost considerations for Cortex AI FunctionsShow comments0Show commentsCommunity DiscussionNo comments yet. Be the first to start the discussion!
Community Discussion