API authentication restrictions: enterprise/organization settings endpoints require classic or OAuth tokens, not GitHub Apps or fine-grained PATs
Automation and CI/CD workflows using GitHub Apps or fine-grained personal access tokens cannot manage enterprise/organization code review settings; only repository-level settings support these modern auth methods.
Evidence
+The enterprise and organization settings endpoints, including the organization runner endpoint, don't support GitHub Apps or fine-grained personal access tokens. The repository settings endpoints support both, with Administration: read permission to read settings and Administration: write permission to update them.
GitHub Copilot now available in Xcode's native coding assistant with public preview support
Xcode developers can now use Copilot directly in the IDE's built-in coding assistant (Xcode 27.3 beta+), supplementing the existing extension-based integration
Evidence
+You can now work with GitHub Copilot directly in Xcode's built-in coding assistant, bringing Copilot into your native Xcode workflow. The integration is now in public preview, available starting with Xcode 27.3 beta.
Copilot usage metrics API now tracks BYOK (bring your own key) usage separately from Copilot-hosted models
Enterprise and organization administrators can now monitor and govern BYOK usage, understand costs separately from Copilot-hosted usage, and distinguish between local BYOK and enterprise custom models in usage reports
Evidence
+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.
GitHub Copilot Fusion is now generally available with intelligent multi-model routing and orchestration.
Developers can now use Copilot Fusion to automatically route tasks to the best model without manual selection. Copilot Fusion offers three effort levels (Standard, High, Max) and uses three execution patterns (Single, Cascade, Critique) to optimize performance and cost.
Evidence
+GitHub Copilot Fusion is generally available. Instead of picking a model for each task, choose Copilot Fusion and let Copilot intelligently route and orchestrate which models it uses for you.
Users on paid Copilot plans receive 30% discount on model costs when using Copilot Fusion for a limited time.
Paid Copilot plan users get cost savings on Copilot Fusion usage during the promotion period. Standard billing applies after the promotional period ends.
Evidence
+When you use Copilot Fusion you're billed for each model it uses, at each model's standard rate. For a limited time, users on paid Copilot plans will receive a 30% discount on model costs when using Copilot Fusion.
Copilot model policy API now generally available for enterprise, teams, and orgs
Enterprise customers can now programmatically manage Copilot model availability across their entire organization using REST API endpoints at enterprise, team, app, and organization levels.
Evidence
+GET and PATCH endpoints are now generally available for model policies at four levels:
Enterprise: /enterprises/{enterprise}/copilot/model-policies
Enterprise teams: /enterprises/{enterprise}/teams/{team_slug}/copilot/model-policies
Enterprise apps: /enterprises/{enterprise}/copilot/apps/model-policies
Organization: /orgs/{org}/copilot/model-policies
Six Copilot models deprecated effective October 19, 2026
Users must migrate from Gemini 3.7 Flash, GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT-5 mini, and Grok 4.5 to their suggested alternatives. Enterprises need to update workflows and enable alternative models through model policies.
Evidence
+As of today, October 19, 2026, we have deprecated the following models across most GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions).
Model | Deprecation date | Suggested alternative
Gemini 3.7 Flash | 2026-10-19 | Gemini 3.8 Flash
GPT-5.5 | 2026-10-19 | GPT-6.1 Sol
GPT-5.4 | 2026-10-19 | GPT-6.1 Sol
GPT-5.4 mini | 2026-10-19 | GPT-6 Luna
GPT-5 mini | 2026-10-19 | GPT-6 Luna
Grok 4.5 | 2026-10-19 | Grok 4.7
HydraFusion Max introduced as new tier with frontier capability for demanding tasks
Users on Copilot Pro, Pro+, Business, and Enterprise plans can now choose between HydraFusion (balanced) and HydraFusion Max (highest capability) for different task requirements.
Evidence
+HydraFusion Max is built on the same architecture and uses the same workflow techniques as HydraFusion, but is tuned for frontier capability on more demanding tasks. It applies higher reasoning efforts where depth and thoroughness matter most, while still using orchestration to consider token efficiency.
Four AI models deprecated in GitHub Copilot: Gemini 3.5/3.6 Flash, Kimi K2.7 Code, and Claude Opus 4.7
Users relying on these models must migrate to alternatives (Gemini 3.8 Flash, Kimi K3, Claude Opus 5.5). Enterprise administrators need to enable alternative models in policies. Workflows and integrations require updates.
Evidence
+As of today, October 2, 2026, we have deprecated the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). [Table showing: Gemini 3.5 Flash → Gemini 3.8 Flash, Gemini 3.6 Flash → Gemini 3.8 Flash, Kimi K2.7 Code → Kimi K3, Claude Opus 4.7 → Claude Opus 5.5]
HydraFusion research preview now available in VS Code and GitHub Copilot app
Copilot Pro, Pro+, Business, and Enterprise users can now use HydraFusion's multi-model orchestration in VS Code and the GitHub Copilot desktop app, expanding beyond CLI.
Evidence
+The HydraFusion research preview is now available in Visual Studio Code and the GitHub Copilot app, expanding beyond Copilot CLI.
Usage metrics API adds pull request review stage timing data
Teams can now analyze where time is spent in the pull request review process (ready to first review, first to final review, final review to merge) with median and 90th percentile metrics, enabling better identification of bottlenecks.
Evidence
+The enterprise and organization repository-level Copilot usage metrics reports now break down how long pull requests spend in each stage of review. A new pull_request_review_times array on each repos-1-day row reports a median and a 90th percentile for the time from ready for review to first review, first review to final review, and final review to merge.
Copilot code review now available on all plans with new dedicated settings page and enterprise-wide configuration.
All Copilot users (Business and Enterprise included) can now access personal code review settings previously limited to Pro/Pro+/Max plans, with new granular controls for automatic reviews and review effort levels.
Evidence
+Previously, personal Copilot code review settings were available only with Copilot Pro, Pro+, and Max on the "Copilot features" page... Under your profile → Copilot settings, a dedicated "code review" page under Copilot is now available on every Copilot plan, including Copilot Business and Copilot Enterprise.
Users should be aware that Claude Opus 5.5 outputs are watermarked, though this does not affect quality, readability, or token cost.
Evidence
+Claude Opus 5.5 watermarks its text outputs. The watermark doesn't change the meaning, quality, or readability of outputs, nor does it add any tokens or cost.
Enterprise and organization report APIs now include feature engagement breakdown and improved adoption phase reporting
Developers building on Copilot APIs can access new `copilot_feature_engagement`, `totals_by_feature`, and `users_in_phase_28d` fields in 28-day aggregate reports. This provides more granular insights into feature adoption across seven different Copilot experiences.
Evidence
+`copilot_feature_engagement`: Adds the dashboard's active-user total and feature engagement counts to enterprise and organization 28-day aggregate reports. `totals_by_feature`: Breaks engagement down by code completion, agent edit, passive Copilot code review, active Copilot code review, Copilot cloud agent, Copilot CLI, and Copilot app. `users_in_phase_28d`: Reports the full rolling 28-day population classified into each AI adoption phase as of that day.
Copilot budget increase requests workflow now generally available
Organization and enterprise owners can now approve, adjust, or deny member budget requests directly in settings. Members can request more AI credits when they hit their limit instead of being blocked from Copilot features.
Evidence
+Previously, when a member used all the Copilot AI credits available to them, they were blocked from Copilot features that consume credits. This release adds a flow for them to request more budget the moment they hit the limit. You can approve, adjust, or deny that request without leaving your settings.
Copilot usage charges based on model auto selects; 10% discount for paid subscribers continues
Paid subscribers maintain their existing 10% discount on auto-selected model usage, though final charges depend on which model is selected by the auto feature.
Evidence
+Usage is charged based on the model auto selects, regardless of tier. Paid subscribers continue to receive a 10% discount on usage billed through auto.
MAI-Code-1-Flash model deprecated across all GitHub Copilot experiences
Users of GitHub Copilot Chat, inline edits, ask and agent modes, and code completions must migrate to MAI-Code-1.1-Flash. Copilot Enterprise administrators need to enable the alternative model through model policies.
Evidence
+We have deprecated MAI-Code-1-Flash across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions) today, September 10, 2026.
Enterprise managed permissions for Copilot agent operations
Administrators of GitHub Copilot Business/Enterprise can now centrally control agent operations (shell commands, file reads/edits, network domains) with blocked, approval-required, or allowed states. This provides fine-grained security controls across the Copilot app, CLI, and VS Code.
Evidence
+If you administer GitHub Copilot Business or GitHub Copilot Enterprise, you can now centrally control which agent operations are blocked, require human approval, or can proceed without a prompt. Managed permissions cover shell commands, file reads and edits, and network domains.
Multiple GitHub Copilot models deprecated on October 2, 2026
Users relying on Gemini 3.5 Flash, Gemini 3.6 Flash, Kimi K2.7 Code, or Claude Opus 4.7 must migrate to suggested alternatives before October 2, 2026. Administrators need to enable alternative models in Copilot settings.
Evidence
+We will deprecate the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions) on October 2nd, 2026:
Model | Deprecation date | Suggested alternative
Gemini 3.5 Flash | 2026-10-02 | Gemini 3.8 Flash
Gemini 3.6 Flash | 2026-10-02 | Gemini 3.8 Flash
Kimi K2.7 Code | 2026-10-02 | Kimi K3
Claude Opus 4.7 | 2026-10-02 | Claude Opus 5
Enterprise-managed settings now support configurable default models for Copilot conversations
Enterprise administrators can now set preferred default models globally or per-team, and teams can override defaults if configured as overridable. This provides more flexibility in managing Copilot deployments across enterprises.
Evidence
+You can now set your preferred GitHub Copilot model as the default for new conversations through enterprise-managed settings. This lets you choose the default model that best fits your workflows.
GitHub Copilot introduces new tiered pricing structure with four plans: Free, Pro, Pro+, and Max
Users now have granular pricing options ranging from free (with limitations) to $100/month for enterprise-grade usage. Organizations must choose between Pro ($10), Pro+ ($39), or Max ($100) per user.
Evidence
+Free
For getting started with GitHub Copilot.
$0USD
Pro
For everyday coding with agents in GitHub Copilot.
$10USDper user / month
Pro+
For more complex development with premium models.
$39USDper user / month
Max
For sustained, high-volume agent workflows with GitHub Copilot.
$100USDper user / month
GitHub Copilot for JetBrains now supports enterprise managed settings for plugin governance, MCP servers, OpenTelemetry, and permissions
Enterprise administrators can now centrally manage and control Copilot plugin governance, MCP server access, telemetry collection, and permission modes across all JetBrains IDE users in their organization.
Evidence
+GitHub Copilot for JetBrains now supports enterprise managed settings for plugin governance, MCP server access, OpenTelemetry, and permission modes. Administrators can now apply consistent controls for everyone on your enterprise's Copilot plan.
Copilot memory feature now available in GitHub Copilot for JetBrains to retain context across chat sessions
Users can maintain context between conversations without repeatedly providing the same project details or preferences. Managed via toggle in Copilot settings portal.
Evidence
+Copilot memory can now retain and recall useful information across agent chat sessions. This helps you maintain context between conversations instead of repeatedly providing the same project details or preferences.
Copilot usage metrics API now reports agent app activity
Enterprise and organization admins can now track usage of individual agent apps (like Claude and Codex agents) through the Copilot usage metrics API in enterprise, organization, enterprise-user, and organization-user reports.
Evidence
+The Copilot usage metrics API now reports that activity, broken out by individual agent. The usage metrics API does this in the enterprise, organization, enterprise-user, and organization-user 1-day and 28-day reports.
Kimi K3 pricing announced: $3 per 1M input tokens, $15 per 1M output tokens, $0.30 per 1M cached input tokens
Users will be charged usage-based pricing for Kimi K3 model, with distinct rates for input, output, and cached input tokens. Pricing documentation rollout temporarily paused due to GitHub Actions incident.
Evidence
+Kimi K3 pricing, which will be $3 per 1M input tokens, $15 per 1M output tokens, and $0.30 per 1M cached input tokens.
Copilot cloud agent now supports customizable reasoning levels for compatible models.
Users on paid Copilot plans (Pro, Pro+, Business, Enterprise, Max) can now control model reasoning depth when delegating tasks, trading off answer quality against token/credit consumption.
Evidence
+When you delegate a task to GitHub Copilot cloud agent, you can now set the reasoning level for models that support it. This allows you to control how much the model reasons before it responds.
Gemini 2.5 Pro and Gemini 3 Flash models deprecated in GitHub Copilot
Users must migrate from Gemini 2.5 Pro to Gemini 3.1 Pro (Preview) and from Gemini 3 Flash to Gemini 3.6 Flash. Copilot Enterprise administrators need to enable alternative models through policy settings. Deprecated models no longer available in Copilot Chat, inline edits, ask/agent modes, and code completions.
Evidence
+As of today, July 31, 2026, we have deprecated the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions).
Gemini 2.5 Pro 2026-07-31 Gemini 3.1 Pro (Preview)
Gemini 3 Flash 2026-07-31 Gemini 3.6 Flash
GitHub Copilot app now has a dedicated access policy separate from Copilot CLI
Enterprise and organization administrators can now independently control access to the Copilot app through dedicated policies, with three options: Enabled everywhere, Disabled everywhere, or Let organizations decide. Gives more granular control over which Copilot clients teams can use.
Evidence
+The GitHub Copilot app now has its own policy, so you can control who has access to it at the enterprise and organization levels. Until now, access to the Copilot app depended on your GitHub Copilot CLI policy being enabled. From several conversations with customers, we understand that many of you want to manage each client independently. Now the Copilot app and the Copilot CLI each have their own policy, giving you the flexibility and control to enable the right clients for your teams.
Users can now customize Copilot code review with firewall settings, custom setup steps, and independent runner configurations for enhanced security and flexibility.
Evidence
+Copilot code review now utilizes a firewall, custom setup steps, and independent runner configurations.
New repository-level Copilot usage metrics API endpoints available
Enterprise and organization admins can now access per-repository breakdown of Copilot coding agent and code review pull request activity via two new REST API endpoints.
Evidence
+Two new endpoints return a per-repository report for a single day:
<ul>
<li><code>GET /enterprises/{enterprise}/copilot/metrics/reports/repos-1-day?day=YYYY-MM-DD</code></li>
<li><code>GET /orgs/{org}/copilot/metrics/reports/repos-1-day?day=YYYY-MM-DD</code></li>
</ul>
Each response returns the following activity:
<ul>
<li>Pull requests created and merged by Copilot coding agent.</li>
<li>Pull requests reviewed by Copilot code review, with suggestion counts broken down by comment type.</li>
</ul>