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";
Expand description

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

  • PII: Maybe
  • Rewriting behavior: None