cd /news/ai-tools/byok-and-enterprise-custom-models-in… · home › topics › ai-tools › article
[ARTICLE · art-163521] src=github.blog ↗ pub= topic=ai-tools verified=true sentiment=↑ positive

BYOK and enterprise custom models in the Copilot usage API

GitHub added bring-your-own-key (BYOK) and enterprise custom model breakdowns to the Copilot usage metrics API, separating that usage from Copilot-hosted model totals in 1-day and 28-day enterprise and organization reports. Local BYOK appears in new fields including used_local_byok, totals_by_local_byok (split by byok_kind and surface), and daily, weekly and monthly active local BYOK user counts, while enterprise custom models are flagged by a new is_custom_enterprise_model boolean on totals_by_client[].totals_by_model[] entries. GitHub said existing totals are unchanged and that local BYOK figures are a lower bound because they rely on client telemetry, and that report days before the release have no is_custom_enterprise_model data.

by read3 min views1 publishedNov 4, 2026
BYOK and enterprise custom models in the Copilot usage API
Image: GitHub Changelog

Improvement

The Copilot usage metrics API now shows bring your own key (BYOK) usage across GitHub Copilot, so you can separate it from Copilot-hosted model usage. Reports cover two kinds of BYOK:

  • Local BYOK is configured by developers in their client. Requests go from Copilot CLI or the GitHub Copilot app directly to the developer’s provider key or local model. Find it inused_local_byok ,totals_by_local_byok , and active local BYOK user counts.
  • Enterprise custom models are configured by admins in GitHub settings, and requests route through GitHub to your provider. Find them withis_custom_enterprise_model intotals_by_client .

Both appear in enterprise and organization reports, at the user and aggregate level, in 1-day and 28-day reports.

Local BYOK

Local BYOK covers a developer’s own provider key and local models served by tools such as Ollama, Foundry Local, LM Studio, and llama-server.

  • used_local_byok : Whether a user made at least one local BYOK request in Copilot CLI or the Copilot app that day. Appears in user-level reports.
  • totals_by_local_byok : Session, request, prompt, and token counts, broken out bybyok_kind (local_managed ,local_user ,local_auto , orremote_user ) andsurface (copilot_cli orcopilot_app ). Appears in user-level and aggregate reports.
  • daily_active_local_byok_users, weekly_active_local_byok_users, and monthly_active_local_byok_users : Distinct users with local BYOK activity for the day, calendar week, and calendar month. Appears in aggregate reports.

Enterprise custom models

  • Added is_custom_enterprise_model , a boolean on eachtotals_by_client[].totals_by_model[] entry. Its value istrue when the request used a custom model configured for your enterprise or organization. GitHub observes these requests server-side, so the field covers every client, including IDEs.
  • A model used both as a Copilot-hosted model and as a custom model appears as two entries, so the counts stay separate.
  • Custom model entries include real request and token counts.

Why this matters

BYOK usage used to blend into Copilot-hosted totals, because local and custom models often share names with Copilot models. Now you can:

  • Govern BYOK: See who sends requests to their own provider keys, local models, or enterprise custom models, and check that against your BYOK policy.
  • Understand spend: Separate Copilot-hosted usage from usage billed by your own provider or run on free local models, so cost per user reflects what Copilot actually serves.
  • See across all tools: Get one view of AI usage in your enterprise, whichever model or provider your developers choose.
  • Compare efficiency: Group users by BYOK or custom model usage and compare them against the Copilot usage metrics you already track.

Important notes

  • No change to existing totals: BYOK usage is already counted. Local BYOK is a subset oftotals_by_cli andtotals_by_copilot_app , and custom model usage is already intotals_by_client . Existing totals are unchanged.
  • Lower bound for local BYOK: Local BYOK fields rely on client telemetry, so they undercount when telemetry is disabled. Token counts can also undercount because some local providers don’t report token usage. Enterprise custom model counts are observed server-side and don’t have this limitation.
  • Model names: Custom model names use the existing model name normalization, so unrecognized names appear asunknown . Local BYOK usage isn’t broken out by model name.
  • No backfill: Report days before this release don’t includeis_custom_enterprise_model .
  • Access: Available to enterprise owners, enterprise billing managers, organization owners, and anyone with a custom organization or enterprise role that grants theView Copilot Metrics permission. The Copilot usage metrics policy must be enabled.

Visit the Copilot usage metrics API documentation to get started.

── more in #ai-tools 4 stories · sorted by recency
── more on @github 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/byok-and-enterprise-…] indexed:0 read:3min 2026-11-04 · —