Per-model token breakdown in usage reports
GitHub usage reports now provide a detailed per-model breakdown of tokens consumed by AI credits, showing input, output, and cache metrics for each model. This gives users better visibility into their AI spending patterns.
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.
Before, the report showed AI credits without the token detail underneath them, so it was hard to explain a charge or find ways to bring it down. Now you can trace exactly how input, output, and cached tokens add up to each model’s cost, and share those details with your stakeholders.
The token breakdown is available to admins on Copilot Business and Copilot Enterprise, and to anyone on Copilot for individuals.
To get the breakdown, download the AI usage report from the AI usage page in your billing settings. For more information, see Billing reports reference.
The post Per-model token breakdown in the usage report appeared first on The GitHub Blog.
Source: original entry ↗
More from GitHub
Follow GitHub to get its new changes in your feed and email digest.
Copilot model policy API for enterprise, orgs, and teams
REST API endpoints now available to retrieve and update Copilot model policies for enterprises, teams, apps, and organizations, enabling centralized policy management at scale.
GitHub Copilot models deprecated
GitHub has deprecated certain models across GitHub Copilot experiences including Chat, inline edits, and code completions, effective October 19, 2026. Users may need to migrate to supported models.
Some Git over HTTPS may temporarily require authentication
GitHub may temporarily require authentication for clones and fetches of public repositories over HTTPS during periods of unusual traffic to protect service availability.