Skip to main content

GEN_AI__USAGE__INPUT_TOKENS__CACHE_WRITE

relay_conventions::attributes

Constant GEN_AI__USAGE__INPUT_TOKENS__CACHE_WRITE 

Source 
pub const GEN_AI__USAGE__INPUT_TOKENS__CACHE_WRITE: &str = "gen_ai.usage.input_tokens.cache_write";
👎Deprecated:

Use GEN_AI__USAGE__CACHE_CREATION__INPUT_TOKENS (gen_ai.usage.cache_creation.input_tokens) instead.

Expand description

The number of tokens written to the cache when processing the AI input (prompt).

  • Scrubbing: Manual
  • Rewriting behavior: Backfill

§Aliases