GitHub Copilot has another model deadline: four more models retire on October 2, after six left most experiences on September 1. If you recently moved to Claude Opus 4.7, that replacement now needs its own replacement. This guide separates the two waves and the admin checks they require.
The September 1 retirement covered Gemini 3.1 Pro, Claude Opus 4.5, Claude Opus 4.6, Claude Sonnet 4.5, Claude Sonnet 4.6, and Raptor Mini. GitHub’s official migration table names supported alternatives. One exception matters: Sonnet 4.6 remains available to individual annual subscribers.
September 18 update: six more Copilot models retire October 19
GitHub has added a third migration deadline. On October 19, 2026, it will remove Gemini 3.7 Flash, GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT-5 mini and Grok 4.5 across Copilot Chat, inline edits, ask and agent modes, and code completions.
| Retiring model | GitHub suggestion |
|---|---|
| Gemini 3.7 Flash | Gemini 3.8 Flash |
| GPT-5.5 | GPT-5.6 Sol |
| GPT-5.4 | GPT-5.6 Sol |
| GPT-5.4 mini | GPT-5.6 Luna |
| GPT-5 mini | GPT-5.6 Luna |
| Grok 4.5 | Grok 4.6 |
The policy detail matters for Business and Enterprise accounts. Under GitHub’s default model enablement, suggested alternatives are enabled automatically unless an administrator disabled the global default or explicitly disabled that model. Organizations that turned the default off must enable the replacement in Copilot model policies before users can select it.
Treat this as a new wave rather than editing the October 2 checklist in place. Add October 19 to the migration board, test the suggested alternative against the same repository tasks and verify both availability and authorization. GitHub will remove the old entries after deprecation, but it will not prove that your integrations, aliases or instructions now point to the intended replacement.
Read GitHub’s September 18 Copilot retirement notice.
Update checked September 18, 2026. Dates and alternatives come from GitHub. Migration and testing advice is MustHave.ai analysis. Marker: copilot-model-retirement-20261019.
The next Copilot deadline is October 2
GitHub published the next retirement notice on September 3. These are upcoming removals, not models that disappeared on September 1. The notice applies across Copilot experiences, and administrators may need to enable the suggested alternatives in model policies.
| Retires October 2, 2026 | GitHub’s suggested replacement |
|---|---|
| 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 |
Opus 4.7 is the trap in the combined timeline. It appeared in GitHub’s earlier replacement suggestions for Opus 4.5 and 4.6, but it is not a durable destination for a migration you are starting now. Keep the historical table below as a record of that first notice; use the October deadline when choosing a route that must remain supported afterward.
Add a removal date to each model entry in your assignment board. For each job, record the current model, tested successor, policy owner, acceptance test, and last safe switch date. A fallback only counts if the account can actually use it. A launch announcement or a model name in a configuration file is not that test.
For teams adding a new high-capability route at the same time, GPT-6 Astra now has a separate Copilot access and cost check. Do not let a retirement migration silently turn into a blanket upgrade to a more expensive default.
Models retired on September 1
| Retired model | GitHub’s suggested route | What to retest |
|---|---|---|
| Gemini 3.1 Pro | Gemini 3.7 Flash | Long reasoning and tool use |
| Claude Opus 4.5 | Claude Opus 4.7, 4.8, or 5 | Deep review and difficult refactors |
| Claude Opus 4.6 | Claude Opus 4.7, 4.8, or 5 | Agent trajectories and premium use |
| Claude Sonnet 4.5 | Claude Sonnet 5 | Everyday coding and review |
| Claude Sonnet 4.6 | Claude Sonnet 5 | Schema, latency, and cost |
| Raptor Mini | MAI-Code-1.1-Flash | Fast edits and completion quality |
A suggested replacement is not a claim of behavioral equivalence. A faster model can change how often an agent asks for clarification. A more capable model can use more premium requests or take longer paths. A newer model can also follow repository instructions more reliably. The only useful comparison is the work your team assigns.
Find model IDs outside the chat picker
- Enterprise and organization model policies.
- Repository-level Copilot settings and instruction files.
- VS Code profiles, extensions, and workspace settings.
- CLI aliases, agent definitions, and scheduled automation.
- Documentation, onboarding guides, and internal screenshots.
- Cost dashboards that group usage by the old model name.
Search configuration repositories for exact IDs and human-readable names. Treat a silent fallback as a migration event, not a success. If a job quietly moves to a different model, the result may look normal while cost, latency, or approval behavior changes.
Do not confuse availability with authorization
GitHub controls whether a model is offered. Your organization still controls whether that model is allowed for a repository or user group. Replacements may also differ by plan. Confirm that enterprise policy, organization policy, and repository policy all agree before announcing a new default.
Our guide to Copilot billing, retention, and policy changes explains why a model rollout should be reviewed with data boundaries and budget rules, not as a picker-only change.
Use a small assignment board
Pick five real jobs: a familiar bug, a repository-wide search, a test-writing task, a risky dependency change, and a pull-request review. Run each old baseline, where still available, against the candidate replacement with the same repository state and instructions.
Record tests passed, defects introduced, useful review findings, false positives, premium requests, wall time, retries, and human repair minutes. A model that writes more code is not automatically better. The strongest route is the one that produces the most verified work per reviewer minute.
The Sonnet 4.6 exception can hide drift
Individual annual subscribers can still see Sonnet 4.6 while teammates on other plans cannot. That creates an awkward support condition: a maintainer may document a workflow that another developer cannot reproduce. Record the plan and model in debugging reports until the team converges on one supported route.
Do not build a long migration around the exception. It preserves access for a group of users, but it does not reverse GitHub’s broader retirement decision.
Pair the migration with review controls
GitHub also introduced Copilot approval assessments on September 1. Every Copilot review can now report whether it considers a pull request ready, while an actual approval that counts toward branch rules stays off by default. If an admin enables it, later commits dismiss the approval and a fresh review is required.
That feature should not turn a model migration into an approval-policy change. Keep the two decisions separate. First verify review quality on the replacement model. Then decide which paths, if any, an automated approval may cover. The Copilot review effort guide gives a practical risk split for lighter and deeper review.
My verdict: route jobs, not users
Watch the first week after the switch for more than obvious request failures. Compare acceptance rate, reverted commits, review discussion, test failures, and the number of times developers manually select another model. A rising override rate is a routing signal. It may mean the default is wrong for a job class even when the service is technically healthy. Publish the approved assignment board in the repository so the decision is visible where work begins.
Give developers one clear fallback path. When the preferred model is unavailable or performs poorly, the fallback should preserve repository policy and logging rather than encourage an unmanaged personal workaround. Retire the fallback when evidence shows the new primary route is stable.
Update incident and support templates with a model field. "Copilot failed" is not enough when several routes are available. Capture the selected model, plan, editor, extension version, repository policy, and request time. That context separates a retirement issue from a tool outage, policy denial, or model-quality problem and shortens the path to a reproducible report.
A single organization default is convenient and often wasteful. Fast edits, broad code search, security review, and difficult refactoring do not need the same model. Use the retirement to define a small assignment board with one approved primary route and one fallback per job class.
Finish by setting a date to remove legacy names from policy, docs, and dashboards. The migration is complete when the old model no longer appears in configuration or incident reports, not when the picker stops showing it.
Read the primary sources
- Read GitHub’s model retirement notice.
- Review GitHub’s Copilot approval announcement.
- Check the current supported model documentation.
Updated September 4, 2026 with GitHub’s September 3 notice for the October 2 retirements. Earlier retirement dates, replacements, plan exception, and approval behavior come from GitHub. Test design and routing recommendations are Musthave.ai analysis.
Update: Four Copilot model families retire on October 19
Updated September 18, 2026. GitHub scheduled another Copilot model retirement for October 19, 2026. Administrators should treat the date as a policy and workflow migration, not only a model-picker change.
| Retiring model | Suggested replacement |
|---|---|
| Gemini 3.7 Flash | Gemini 3.8 Flash |
| GPT-5.5 and GPT-5.4 | GPT-5.6 Sol |
| GPT-5.4 mini and GPT-5 mini | GPT-5.6 Luna |
| Grok 4.5 | Grok 4.6 |
GitHub says suggested replacements are automatically enabled only when an organization uses default model enablement. An explicit policy choice can prevent the new model from appearing. Before October 19, inspect organization and enterprise policy, repository instructions, custom agents, scheduled work and scripts that pin a model name.
- Enable the replacement under the intended policy.
- Replay representative coding, review and agent tasks.
- Compare structured output, tool use, corrections and latency.
- Run every scheduled task manually once.
- Remove stale documentation and alert owners before the cutoff.
Primary update source: GitHub Copilot model deprecation notice.
