Token usage and model trace card — shows Gemini call stats inline on a page
| Field | Type | |
|---|---|---|
| model | string (optional, e.g. gemini-2.5-flash) | optional |
| prompt_tokens | integer | optional |
| thinking_tokens | integer | optional |
| output_tokens | integer | optional |
| total_tokens | integer | optional |
{
"type": "ai_build_trace"
}{
"identifier": "urn:air:a2uicatalog.ai:atom:ai_build_trace",
"displayName": "Ai Build Trace",
"type": "application/vnd.a2ui.atom+json",
"url": "https://a2uicatalog.ai/atoms/ai_build_trace",
"capabilities": [
"apps-script-web"
],
"description": "Token usage and model trace card \u2014 shows Gemini call stats inline on a page",
"representativeQueries": [
"show a Gemini token usage trace card",
"token usage and model trace card \u2014 shows gemini call stats inline on a page",
"render a ai build trace"
]
}The renderer is open source. Deploy your own instance in 4 commands — you own the URL, no dependency on the demo endpoint.
git clone https://github.com/a2uicatalog/a2ui
cd apps-script-surface/gas-schema-renderer
clasp push && clasp deploy