// AI Platform Drift
GitHub Copilot usage API now reports OpenCode and other non-IDE tools
GitHub Copilot changelog · published 2026-10-24 04:39 UTC
WHAT CHANGEDGitHub Copilot's usage metrics API added a totals_by_client array to enterprise, organization, and user-level 1-day and 28-day reports on 23 October 2026. The array captures model requests from tools like OpenCode, Claude Code, Codex, Zed, and others that were previously unreported. Each entry includes request_count, session_count, token_usage (prompt/output tokens), and totals_by_model with a model_selection_mode field showing whether the model was user_selected, auto, or product_selected.
WHY IT MATTERSUsage from tools that don't send editor telemetry was missing from totals_by_ide reports, making it impossible to account for Copilot consumption outside traditional IDEs. Server-side request counting now captures this traffic, so token volume and cost attribution are complete. Organizations paying for Copilot usage can now see which tools drive consumption and make tool support decisions based on actual request and token metrics rather than partial data.
WHAT TO DOPull the updated API response for your enterprise or organization reports and compare totals_by_client request_count and token_usage against your existing totals_by_ide data to identify previously uncaptured usage. If you forecast Copilot costs or allocate them by team, add the new client breakdown to your reporting. Note that request_count measures model calls, not prompts, so one prompt may generate multiple requests.
Model-reported confidence 85% (not measured accuracy)
Primary source ↗
written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
+## Usage metrics API adds usage from tools like OpenCode +https://github.blog/changelog/2026-10-23-usage-metrics-api-adds-usage-from-tools-like-opencode +Fri, 23 Oct 2026 23:42:03 +0000 + +The Copilot usage metrics API now reports model usage from more of the tools your developers use with Copilot, including tools like OpenCode that weren’t previously captured in your reports. A new totals_by_client array is available in the enterprise, organization, enterprise-user, and organization-user 1-day and 28-day reports. +What’s new +Each totals_by_client entry represents one client and includes: + +client: The tool that sent the requests, such as opencode, claude_code, codex, zed, copilot_cli, github_app, cloud_agent, code_review, vscode, or jetbrains. Unrecognized clients are grouped under other. +request_count: The number of successful model requests from the client. +session_count: The number of distinct sessions from the client. +token_usage: Prompt tokens, output tokens, and average tokens per request. +totals_by_model: The same request and token metrics broken down by model, with a model_selection_mode that shows whether the model was requested directly (user_selected), chosen by auto (auto), or chosen by the product (product_selected). Selection modes that aren’t reported individually yet appear as other, and values that can’t be normalized appear as unknown. + +Why this matters +More developers now use Copilot as the model provider behind tools outside the IDE. Because those tools often don’t send editor telemetry, their usage was missing from totals_by_ide and hard to account for. Counting requests on the server closes that gap, so you can see which tools drive Copilot usage, compare request and token volume across them, and base tool support and governance decisions on real usage. +This is different from agent app activity, which counts jobs started by agent apps such as Claude and Codex on GitHub. totals_by_client measures model traffic, meaning requests and tokens, from any tool that uses Copilot. +Important notes + +Scope: Enterprise, organization, enterprise-user, and organization-user reports, in both 1-day and 28-day versions. In the aggregated 28-day reports, totals_by_client appears in each day_totals entry. +Access: Available to enterprise owners and billing managers, organization owners, and anyone with a custom organization or enterprise role that grants the View Copilot Metrics permission. The Copilot usage metrics policy must be enabled. +Copilot code review and Copilot cloud agent: Requests from these clients report product_selected because the product chooses the model. Copilot code review models are reported as unknown. +Request counts: request_count counts model calls, not prompts. One prompt can trigger several model calls, so don’t compare this field directly with prompt or interaction counts. +Client identification: Clients are identified by the integration ID they send with each request. Treat client as a best-effort grouping, not a verified identity. +Backward compatibility: This change is additive. Existing fields are unchanged, and totals_by_client is an empty array when there is no usage to report. + +Visit the Copilot usage metrics API documentation to get started. + +The post Usage metrics API adds usage from tools like OpenCode appeared first on The GitHub Blog.
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
| triage verdict | MATERIAL at 0.92, needed 0.5 |
|---|---|
| triage reasoning | API expansion adds new reportable fields and client coverage affecting usage visibility and governance decisions. |
| signals | new API field added (totals_by_client array) · expanded metric coverage (previously uncaptured tools now reported) · new client types enumerated (opencode, claude_code, codex, zed, copilot_cli, github_app, cloud_agent, code_review, vscode, jetbrains) · new token_usage breakdown available · new model_selection_mode field (user_selected, auto, product_selected) · scope clarification: enterprise, organization, user-level reports affected · permission requirement stated (View Copilot Metrics) · behavioral note: request_count != prompt count |
| suppression | — |
| triage model | anthropic/claude-haiku-4.5 ($0.00000) |
| writer model | anthropic/claude-sonnet-4.5 ($0.00000) |