Routing mix by alias family

Distribution of resolved requests across the alias families in the catalog.

All trends

-38 % of requests over window

code.*

auto.balanced

auto.fast

auto.cheapest

reasoning.best

vision.*

Measured in % of requests.

What this trend means.

Coding aliases dominate. The long tail toward reasoning.best is small but disproportionately expensive, which is where alias releases earn their keep.

Tie-in

Trends describe the population; a diagnostic measures you. The two together tell you whether you are ahead of or behind the curve on reuse.

Other trend series.

Workloads with a >10k-token stable prefix

% of workloads

Median realized reuse ratio

% of input tokens

Share of non-interactive tokens on batch tiers

% of background tokens

Measure your reuse against the trend.

Run a diagnostic and see where your workload sits relative to these aggregate patterns.

Run a diagnostic The benchmark