QuestionQ75

Snowflake Gen AI Governance

A user needs to enable cross-region inference in a Snowflake account that is located in the AWS us-east-1 (N. Virginia) region, so that they can access LLM models available in other AWS regions.

What considerations should be made before enabling cross-region inference in the Snowflake account?

Choose three
  • A The user needs to use the ORGADMIN role.
  • B The user needs to use the ACCOUNTADMIN role.
  • C Credits related to the inference requests will be consumed based on the price per service consumption rates in the AWS us-east-1 region.
  • D Credits related to the inference will be consumed based on the price per service consumption rates in the region where the LLM is located.
  • E The data required for the inference request will stay within the AWS global network.
  • F The data required for the inference request will stay within the requesting region.
Explanation

Enabling cross-region inference requires setting the account-level parameter CORTEX_ENABLED_CROSS_REGION, which can only be modified using the ACCOUNTADMIN role via the ALTER ACCOUNT command (ORGADMIN cannot set it). Billing for LLM inference credits is based on the requesting region's service consumption rates — Snowflake documentation states that credits are considered consumed in the requesting region even when the actual processing occurs in a different region. Finally, because the source account is on AWS and the destination LLM region is also on AWS (the same cloud service provider), inference traffic is routed over the AWS private backbone network rather than the public internet, meaning the data stays within the AWS global network during transit, though it is not confined solely to the requesting region.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!