Checked fact 34522 Nov 2026Agents and apps

The same conventions list gen_ai.usage.input_tokens and gen_ai.usage.output_tokens as Recommended attributes of the agent invocation span.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

`gen_ai.usage.input_tokens` | Development | `Recommended` | int | The total number of input (prompt) tokens across all modalities. ... `gen_ai.usage.output_tokens` | Development | `Recommended` | int | The total number of output (completion) tokens across all modalities.

What the source said when we opened it, on 2 Nov 2026.

The source

Semantic Conventions for GenAI agent and framework spans
OpenTelemetry (GitHub)

Open the source archived copy

Checked

Checked by the notis newsroom on 2 Nov 2026, against the source above.

In the story

How an agent trace records each model call and tool call 2 Nov 2026

Cite this fact

Short permanent address

In a sentence

“The same conventions list gen_ai.usage.input_tokens and gen_ai.usage.output_tokens as Recommended attributes of the agent invocation span.” ai notis, checked 2 Nov 2026. Source: Semantic Conventions for GenAI agent and framework spans (OpenTelemetry (GitHub)). https://ainotis.com/c/3452

As a reference (APA style)

ai notis. (2026, November 2). The same conventions list gen_ai.usage.input_tokens and gen_ai.usage.output_tokens as Recommended attributes of the agent invocation span [Checked claim 3452]. ai notis. https://ainotis.com/c/3452

Anyone may quote this address. It does not change; if we correct the story, this page says so.