Usage
In this section, users can view the number of models that consumed tokens, the total tokens consumption, the total input tokens, the total output tokens, the total prompt cache tokens, and other relevant information under their account. They can also customize the time period for queries based on their needs.
Experience Link：Usage
Online Inference
Usage List
This section provides statistics on the model usage for users' online inference. Users can view the following information:
Screenshot | Description |
|
Usage Details
Consumption Trend
After selecting a specific model on the "Usage" page, users will see the usage consumption trend for that model. Users can view the trends in total tokens consumption, input tokens, and output tokens through line charts.
In the input token table, users can view detailed consumption breakdowns by input type, such as tokens from text, images, and audio.In the output token table, users can view detailed consumption breakdowns by output type, such as tokens generated during thinking and non-thinking processes.
Notice：The usage details for model trials only support filtering by aggregation dimensions and statistical periods.
Consumption Details
Users can view the details of resource consumption for all inference services under this model. Clicking on the service name will redirect to the details page of the corresponding inference service.