GitHub Models Is Retired as Copilot CLI and AI Credit Migration Moves Into Execution
The playground, model catalog, inference API, and BYOK have stopped, so ENHE's July 3 preview is updated with the confirmed status and a migration checklist
Key takeaways
GitHub Models was fully retired on July 30, 2026. The playground, model catalog, inference API, and bring-your-own-key access are no longer available, including for customers with active usage. ENHE's July 3 page had already documented the announced retirement date; this update changes the event from a future plan to a confirmed production state and adds migration checks. GitHub points users who need direct model access toward Microsoft Foundry and users building AI workflows on GitHub toward GitHub Copilot. Teams should inventory endpoints, keys, billing ownership, rate limits, model behavior, and rollback paths before replacing the retired service. The Copilot CLI and AI credit guidance remains relevant for governed automation.
# GitHub Models Is Retired as Copilot CLI and AI Credit Migration Moves Into Execution
Published or updated: July 31, 2026
Table of contents
- Direct answer
- Fact sources
- Action steps
- Why it matters
- Impact for ordinary AI users
- Related tools and tutorials
- FAQ
- Source links
Direct answer
GitHub Models is now retired. As of July 30, 2026, the playground, model catalog, inference API, and BYOK are unavailable to both new and existing customers. Projects that need direct model access can evaluate Microsoft Foundry, while users building AI workflows inside GitHub can evaluate GitHub Copilot. The two paths differ in model scope, billing, credentials, permissions, and rate limits.
Fact sources
GitHub published the final retirement notice on July 30, 2026. It says the GitHub Models playground, model catalog, inference API, and BYOK are no longer available to any customer, including existing customers with active usage. This completes the retirement announced on July 1.
GitHub separates the migration guidance into two paths. Projects needing direct model access can review the Microsoft Foundry model catalog. Users building AI-powered workflows directly on GitHub can evaluate GitHub Copilot. The announcement does not claim identical models, APIs, pricing, or compatibility.
ENHE first published this page on July 3 to explain Copilot CLI, AI credit session limits, cost centers, and the scheduled GitHub Models retirement. July 30 was still in the future then. This update changes the retirement from a plan to a confirmed state while preserving the same CMS record and canonical slug.
How to check a migration after GitHub Models retirement
- Inventory every GitHub Models playground workflow, inference endpoint, BYOK credential, model name, repository script, and test-environment reference.
- Separate direct model API needs from AI workflows inside GitHub, then evaluate Microsoft Foundry and GitHub Copilot for their respective tasks.
- Recheck authentication, secret storage, model regions, pricing, rate limits, data retention, and organization billing ownership.
- Use a fixed evaluation set to compare replacement-model output, latency, tool calls, error formats, and safety behavior.
- Add explicit failures and removal dates for retired endpoints so scripts do not silently retry or fall back to an unknown model.
- Switch production workflows only after permissions, cost limits, logs, tests, review, and rollback are verified.
Why it matters
The move from retirement notice to completed shutdown shows that a public model playground cannot be treated as permanent infrastructure. Migration is more than replacing a URL; it includes model behavior, authentication, cost, data boundaries, errors, and organizational ownership. This page retains its Copilot CLI and AI credit guidance because governed automation still needs session limits, repository permissions, and review records.
Impact for ordinary AI users
Users who relied on GitHub Models for comparisons, prototypes, or BYOK should check scripts, extensions, and tutorials for retired references. Users who never used the service do not need to migrate, but the shutdown is still a useful selection lesson: experimental entry points, production APIs, billing accounts, and long-term support must be evaluated separately.
Related tools and tutorials
ENHE's AI news tracks service status, the software catalog supports replacement comparisons, skill tutorials cover migration tests, and account services help users check credentials, permissions, and billing ownership.
AI service status and current news; AI model and software comparisons; AI migration tests and skill tutorials; AI credentials, permissions, and billing services.
FAQ
Can GitHub Models still be used?
No. GitHub says the playground, model catalog, inference API, and BYOK have been unavailable to all customers since July 30, 2026.
Is Microsoft Foundry or GitHub Copilot the direct replacement?
It depends on the task. Microsoft Foundry is a path for direct model access and catalog needs. GitHub Copilot is a path for AI inside GitHub development workflows. They are not the same product.
Do AI credit session limits still matter?
Yes. GitHub Models retirement does not end Copilot CLI or SDK usage. Copilot automation still needs usage limits, permissions, logs, and human review.
Source links
- GitHub Changelog：GitHub Models is now retired（2026-07-30）
- GitHub Changelog：GitHub Models is being fully retired on July 30, 2026（2026-07-01）
- Microsoft Foundry：Models catalog
- GitHub Docs：GitHub Copilot
- GitHub Docs：Use your own API keys with Copilot
- GitHub Blog：Copilot usage-based billing
What this means for everyday users
ENHE users should inventory retired GitHub Models endpoints, model names, and BYOK references, then document authentication, pricing, rate limits, data boundaries, and human review for each replacement.
Related reading
GitHub Copilot Metrics Add OpenCode and Other Clients: Requests Are Not Prompts
GitHub added totals_by_client to the Copilot usage metrics API on October 23, 2026. Enterprise and organization reports can now show model traffic from OpenCode, Claude Code, Codex, Zed, Copilot CLI, GitHub apps, cloud agents, code review, VS Code, JetBrains, and other clients. This article helps administrators build reliable one-day and 28-day reports without confusing model calls with user prompts. It explains request, session, token, model, and selection-mode fields; separates client traffic from agent-app jobs; and adds checks for unknown identifiers, empty arrays, permissions, and coverage. The result is a governance trend report, not an exact invoice or individual productivity score.
Bayer Shares Production Lessons From 22 Specialist Agents: HTTP Success Is Not Task Success
AWS published Bayer Crop Science’s Agentic Decision Engine case study on October 23, 2026. The production system runs 22 specialist agents over governed analytics workflows, models, logs, and visualization tools. This article turns the architecture into five reusable acceptance checks for enterprise agent teams: persist the state needed to resume work, define identity and authorization at every boundary, scope each agent’s tool catalog, distinguish transport success from task success, and release to a gated group before broader access. It also explains why Bayer’s adoption and resolution figures are evidence about one implementation, not promises for another organization. The focus is operational proof, least privilege, rollback, and observable outcomes rather than prompt polish.
GitHub Copilot in Teams Turns Notifications Into Pull Requests: What to Check Before Review
GitHub updated its Microsoft Teams app on October 23, 2026, so an issue notification in a channel, group chat, or private chat can become a Copilot task that investigates the problem, proposes a fix, and opens a pull request. This article helps development and product teams adopt the workflow without mistaking an automated pull request for shipped code. It explains the consolidated app, repository connection, the November 16 retirement of the legacy GitHub app, and the review boundary. A practical acceptance checklist asks teams to reproduce the issue, inspect changed files, run targeted tests, verify permissions, and keep merge and deployment as explicit human decisions.
IskayPet Connects SharePoint to a Managed Knowledge Base: Validate Permissions Before Answers
AWS published IskayPet’s corporate knowledge assistant case study on October 22, 2026. The system connects Amazon Bedrock Managed Knowledge Bases to existing SharePoint repositories and answers cited questions across retail operations, veterinary care, onboarding, and procurement in four languages and three countries. This article turns the case into a practical acceptance plan for knowledge owners. It checks source scope, inherited permissions, hybrid retrieval, duplicate and fragment removal, citation quality, feedback, and token cost before expansion. It also separates the customer’s reported production results from what another organization should expect. A managed retrieval stack reduces infrastructure work, but it does not remove content ownership, access reviews, evaluation datasets, or human verification of important answers.
Copilot in Visual Studio Adds PR Exploration, a BYOM Migration, and NuGet Fixes
GitHub summarized three September updates for Copilot in Visual Studio 2026 on October 22, 2026. The Git agent can explore an attached pull request and link back to comments and files. Bring Your Own Model remains in preview but now requires the new Agent experience, and previously configured Ollama models must be added again. NuGet Audit warnings can open Copilot Chat with the NuGet MCP server to propose dependency fixes. This article gives .NET developers a cautious upgrade checklist: preserve current settings, validate each feature independently, review package and lock-file changes, run targeted tests and vulnerability scans, and keep a rollback path. Summaries and suggested fixes remain review inputs, not verified outcomes.
Amazon Polly Upgrades Generative Speech: Validate 14 New Voices Without Breaking Existing Apps
Amazon Polly upgraded its Generative engine on October 22, 2026, adding 14 voices across nine locales and making generative Hindi and Finnish generally available. Existing voice names and API calls remain unchanged, so applications do not need a code migration, but generated audio can still change. This article gives creators, course teams, contact-center operators, and accessibility teams a reversible acceptance test. It uses one multilingual script to compare pronunciation, pauses, latency, loudness, and fallback behavior before increasing traffic. It also separates the larger voice catalog from a key limitation: generative voices still do not provide speech marks, so workflows that synchronize captions, highlighting, or animation must keep a compatible engine or another timing source.
Summary
A reliable migration begins with an inventory of retired dependencies, then separates direct model access from AI workflows inside GitHub. The move is complete only when replacement permissions, cost, behavior, and rollback have been verified.