gen_ai.usage.cache_read.input_tokens
MovedGenAI registryintas of v1.44.0
The number of input tokens served from a provider-managed cache.
The value SHOULD be included in gen_ai.usage.input_tokens.
Examples
- 50
Used by
events (1)
- gen_ai.client.inference.operation.details
spans (7)
- span.anthropic.inference.client
- span.aws.bedrock.client
- span.azure.ai.inference.client
- span.gen_ai.inference.client
- span.gen_ai.invoke_agent.client
- span.gen_ai.invoke_agent.internal
- span.openai.inference.client
* required on that signal.
History
- v1.42.0deprecated
Moved to the OpenTelemetry GenAI semantic conventions repository.
Added as development.