Variable ATTR_GEN_AI_USAGE_CACHE_READ_INPUT_TOKENS`Const` `Experimental`

ATTR_GEN_AI_USAGE_CACHE_READ_INPUT_TOKENS: "gen_ai.usage.cache_read.input_tokens" = ...

The number of input tokens served from a provider-managed cache.

Example

Note

The value SHOULD be included in gen_ai.usage.input_tokens.

This attribute is experimental and is subject to breaking changes in minor releases of @opentelemetry/semantic-conventions.

Deprecated

Moved to the OpenTelemetry GenAI semantic conventions repository.