RunStatistics
A summary of the runs in a time range.
Shape: object
| Property | Required | Type | Description | Rules |
|---|---|---|---|---|
totalRuns |
yes | integer (int64) |
The total number of runs matching the filter. | pattern `^-?(?:0\ |
completedRuns |
yes | integer (int64) |
The number of runs that completed successfully. | pattern `^-?(?:0\ |
failedRuns |
yes | integer (int64) |
The number of runs that ended in an error. | pattern `^-?(?:0\ |
canceledRuns |
yes | integer (int64) |
The number of cancelled runs. | pattern `^-?(?:0\ |
runningRuns |
yes | integer (int64) |
The number of runs still running. | pattern `^-?(?:0\ |
awaitingInputRuns |
no | integer (int64) |
The number of runs awaiting human input. | pattern `^-?(?:0\ |
inputTokens |
no | integer (int64) |
The total input tokens. | pattern `^-?(?:0\ |
outputTokens |
no | integer (int64) |
The total output tokens. | pattern `^-?(?:0\ |
totalTokens |
no | integer (int64) |
The total tokens. | pattern `^-?(?:0\ |
cachedInputTokens |
no | integer (int64) |
The input tokens that were served from the prompt cache. Counted INSIDE InputTokens, so the two must not be added together. |
pattern `^-?(?:0\ |
reasoningTokens |
no | integer (int64) |
The tokens spent on reasoning. Counted INSIDE OutputTokens. |
pattern `^-?(?:0\ |
audioInputTokens |
no | integer (int64) |
The audio input tokens. Counted INSIDE InputTokens. |
pattern `^-?(?:0\ |
audioOutputTokens |
no | integer (int64) |
The audio output tokens. Counted INSIDE OutputTokens. |
pattern `^-?(?:0\ |
byAgent |
no | array of RunAgentStatistics |
The breakdown by agent. | — |
byModel |
no | array of RunModelStatistics |
The breakdown by model. Runs with an unknown model name do not appear in this list; they are still counted in the totals. | — |
byVersion |
no | array of RunVersionStatistics |
The breakdown by definition version. Runs with an unknown version do not appear in this list. | — |
byUser |
no | array of RunUserStatistics |
The breakdown by user. Runs that carry no user identity do not appear in this list; they are still counted in the totals. | — |
byLabel |
no | array of RunLabelStatistics |
The breakdown by label. One entry per distinct key/value pair, so a run carrying three labels contributes to three entries. | — |
byErrorClass |
no | array of RunErrorStatistics |
The breakdown by error class. Only runs that ended in an error are counted. Rows written before the error class was added appear in the Unknown bucket (past rows are not backfilled). |
— |
totalCost |
no | number (double) |
The total cost. If a model has undefined pricing, that model’s run costs are not included in this total (only runs with known pricing are summed); the number of runs excluded appears in RunsWithUnknownPricing. null if no run was ever priced. |
pattern `^-?(?:0\ |
currency |
no | string |
The currency. Populated when TotalCost is populated. |
— |
runsWithUnknownPricing |
no | integer (int64) |
The number of runs whose model is known but whose pricing is undefined. | pattern `^-?(?:0\ |
errorRate |
no | number (double) |
The error rate among settled runs (0–1). null if no run has settled. |
pattern `^-?(?:0\ |
scoredRuns |
no | integer (int64) |
The number of runs that received at least one RunScore (at the run or message level). Eval runs (RunKind.Eval) are excluded for the same reason as TotalRuns. |
pattern `^-?(?:0\ |
positiveRate |
no | number (double) |
The positive rate among RunScoreKind.Binary scores (0–1). Star ratings are not included in this rate — averaging the two kinds would be meaningless. null if there is no binary score. |
pattern `^-?(?:0\ |