Skip to main content

Model Usage Ranking

To help you understand how the built-in models on the CloudBase AI platform are actually used, we update the usage distribution of the platform's models periodically.

Token Usage Distribution​

Measured by the total token volume of all text models on the platform (input tokens + output tokens, including cache hits), based on full calendar days (Beijing Time).

Share of token volume by model · normalized to 100% per day
7 sampled days
Each bar is normalized to 100% of that day's total across the 7 sampled days, in chronological order from left to right; the right panel shows the cumulative share by default and switches to the hovered day's share, while hovering a legend entry keeps only that model's segments so its trend stands out. Values are merged from raw modelTags into model families, with the long tail not listed individually grouped into Other; days excluded from the sample are separated by a dashed line.

Request Volume Distribution​

Measured by the number of invocations of all models on the platform, based on full calendar days (Beijing Time).

Share of requests by model · normalized to 100% per day
7 sampled days
Each bar is normalized to 100% of that day's requests across the 7 sampled days, in chronological order from left to right; the right panel shows the cumulative share by default and switches to the hovered day's share, while hovering a legend entry keeps only that model's segments so its trend stands out. Request counts are merged from raw modelTags into model families, with the long tail not listed individually grouped into Other.