Enhanced Visibility for Model Usage

GitHub Copilot's usage metrics now provide complete transparency into which models your teams are actually using when auto model selection is enabled. Previously, all activity under auto mode appeared under a generic "Auto" label, obscuring which specific models were handling requests. This update resolves those auto-selected models to their actual names.

What's Changed

The improvement spans multiple reporting surfaces:

• REST API: The totals_by_model_feature endpoint now breaks down model usage accurately across enterprise, organization, and user-level reports
• Dashboard: "Model usage per chat mode" charts display specific model names instead of generic auto labels
• Data rollup: Auto mode usage is automatically rolled into the resolved model totals for seamless reporting

Why This Matters for Organizations

• Compliance & Auditing: Organizations can now generate accurate model-level reports for compliance workflows
• Resource Planning: Admins gain visibility into which models are powering their teams' Copilot usage, enabling better resource allocation decisions
• Scalability: As auto mode adoption grows across teams, metrics remain clear and actionable

What You Need to Know

The auto usage is consolidated into the resolved model totals—there isn't yet a separate breakdown showing auto vs. manually selected model preferences. However, GitHub notes this is being considered for a future release. Existing integrations with the Copilot usage metrics REST API will automatically benefit from this enhanced reporting without requiring changes.