Tools #Coding agents Oct 25, 2026 · Originally published Oct 23

The Copilot usage metrics API now breaks usage out by client, listing requests and tokens from Claude Code, Codex, OpenCode and other tools

The IDE is no longer the only way developers reach Copilot's models. This covers what the new totals_by_client field shows and which numbers you shouldn't compare directly.

Primary source GitHub Changelog · github.blog Read the original ↗

// Key points

The 1-day and 28-day reports for enterprises, organizations and their users gain a totals_by_client array. Client values include opencode, claude_code, codex, zed, copilot_cli, cloud_agent, code_review, vscode and jetbrains; unrecognized tools fall under other.
Each client gets successful model requests, sessions, prompt and output tokens and average tokens per request, broken down by model with a model_selection_mode of user-selected, auto or product-selected.
request_count counts model calls, not prompts, so one prompt can produce several. Clients are identified by the integration ID each request sends, which GitHub says is a best-effort grouping, not a verified identity.
The change is additive and existing fields are unchanged. It needs the Copilot usage metrics policy enabled, and is visible to enterprise owners, billing managers, organization owners and custom roles with View Copilot Metrics.

Builder's takePut this next to the 10-24 change that named custom skills and MCP servers in the metrics: Copilot is turning into the shared model bill for several coding tools. I'd pull a 28-day report, see which client the tokens go to, and only then pick the team's default tool; just don't compare request_count with prompt counts, or treat client as audit evidence.

// Background · from #Coding agents

Full timeline →