A data scientist is leveraging various Snowflake Cortex LLM functions to process extensive text data for an application. To effectively manage their budget, they need a clear understanding of how costs are incurred for each specific function. Which of the following statements accurately describe how costs are calculated for Snowflake Cortex LLM functions, with a particular focus on token usage?

Correct Answer: B,D
Option B is correct because for the 'EXTRACT_ANSWER function, the number of billable tokens is the sum of the tokens in the Trom_text' (source_document) and 'question' fields. Option D is correct as for 'CLASSIFY TEXT (or labels, descriptions, and examples provided in the categories are counted as input tokens for each record processed, which directly increases the cost. Option A is incorrect because 'EMBED TEXT 768' and 'EMBED TEXT 1024' functions only count 'input tokens' towards the billable total, not both input and output tokens. Option C is incorrect because Cortex Structured Outputs does not incur additional compute cost for the overhead of verifying tokens against the supplied JSON schema, although schema complexity can increase total token consumption. Option E is incorrect because (and 'SNOWFLAKE.CORTEX.PARSE_DOCUMENT) billing is based on the 'number of document pages processed' (e.g., 3.33 Credits per 1 ,000 pages for Layout mode), not just the number of documents. For paged formats (PDF, DOCX), each page is billed as a page; for image files, each image is a page; for HTML/TXT, each 3,000 characters is a page.