Per-model token breakdown in the usage report

You can now see a per-model breakdown of the tokens behind your AI credits in the usage report. For each model, the AI usage report shows the input, output, cache… The post Per-model token breakdown in the usage report appeared first on The GitHub Blog.

What happened

This feature allows developers to analyze their token consumption by model, offering transparency in how AI credits are utilized in their workflows.

Why it matters

Understanding token breakdown helps developers optimize the use of AI resources, allowing for more informed decisions on which models to utilize based on cost-efficiency and performance.

Sources