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 read, and cache write tokens alongside the AI credits it consumed.
Read GitHub's release noteshttps://github.blog/changelog/2026-08-11-per-model-token-breakdown-in-the-usage-report
Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.
More GitHub Copilot releases
Also shipped on Aug 11, 2026
ABAC GRANT policies now cover Unity Gateway resource types (Beta)
BetaAI agentsMCPGovernance
Unity Catalog ABAC GRANT policies support more securable types in Beta
BetaAI agentsMCPGovernance