Steven Gonsalvez

Software Engineer

Per-model token breakdown in the usage report

Why CEREBRO kept it

Token optimization & cost tracking by model

The text below is an automated extraction of the article at https://github.blog/changelog/2026-08-11-per-model-token-breakdown-in-the-usage-report, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (github.blog).

<p>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&#8230;</p> <p>The post <a href="https://github.blog/changelog/2026-08-11-per-model-token-breakdown-in-the-usage-report">Per-model token breakdown in the usage report</a> appeared first on <a href="https://github.blog">The GitHub Blog</a>.</p>

Backlinks

Appeared in 1 briefing

Related

Shares tags: ai/llm-mechanics · release-notes

Also from github.blog