semconv.com

gen_ai.usage.reasoning.output_tokens

MovedGenAI registryintas of v1.44.0

The number of output tokens used for reasoning (e.g. chain-of-thought, extended thinking).

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

Examples

Used by

events (1)

  • gen_ai.client.inference.operation.details

spans (5)

  • span.anthropic.inference.client
  • span.aws.bedrock.client
  • span.azure.ai.inference.client
  • span.gen_ai.inference.client
  • span.openai.inference.client

* required on that signal.

History

  1. v1.42.0deprecated

    Moved to the OpenTelemetry GenAI semantic conventions repository.

  2. v1.41.0

    Added as development.

Definition sourceRegistry docsJSON