Short answer. Pin a versioned model for production, monitor the provider's deprecation page and your own model inventory, and keep a tested replacement ready. Notice periods range from about two weeks to twelve months. A “latest” alias is convenient, but it can change behaviour without a deploy.
What a deprecation policy must answer
A useful policy answers four questions: how much notice you get, how you are notified, what happens to requests after the date, and whether you can keep the old model through a dedicated deployment. Most provider pages answer the first two and are vague about the last two. Read the model card, not just the marketing page.
| Question | Why it matters | Where to look |
|---|---|---|
| Notice period | Sets the migration runway | Deprecations or lifecycle page |
| Notification channel | Email can go to a dead alias | Email, status page, API field |
| Post-retirement behaviour | Error, redirect or silent re-point | Model card and changelog |
| Extension option | Dedicated capacity may outlive the date | Sales terms or contract |
The 12-provider notice table
These are the periods each provider publishes, not the notice every retirement actually received. A provider can shorten a window for safety, security or low usage. Check the source page before planning a release.
| Provider | Published notice | At retirement |
|---|---|---|
| OpenAI | GA 6 months; specialized 3 months; preview ~2 weeks | Requests fail; shutdown_date in models API |
| Anthropic | At least 60 days for public models | Requests fail |
| Google (Vertex / Gemini API) | Vertex 12 months after release or 45 days for short-term; Gemini API no fixed minimum, preview ~2 weeks | Requests fail or route |
| Microsoft Foundry / Azure OpenAI | 18-month GA lifecycle; 60 days notice; preview 30 days | 410 Gone; some deployments auto-upgrade |
| AWS Bedrock | 12 months + 6 months Legacy before 7 Sep 2026; per-card 6 months or 45 days after | Requests fail; no automatic migration |
| Mistral | GA 6 months; Labs, Preview and third-party 1 month | 404 |
| Cohere | No fixed period; existing users keep access until shutdown | Requests fail |
| Together AI | 2–3 weeks serverless; preview under 24 hours after 30 days | Removed from serverless |
| Groq | No fixed period; dated notice per model | Requests fail |
| Fireworks AI | At least 2 weeks for serverless | Requests fail |
| DeepSeek | No standing policy; changelog only | Requests fail or temporarily route |
| xAI | No general minimum; 60 days on the 2026 Imagine retirement | Retired slugs may redirect |
Two lessons: floors are not schedules, and a redirect is more dangerous than an error because the application keeps working with a different model.
Sunset calendar: published dates to watch
The dates below were published as of 20 November 2026. They move, and a provider can add a date after this page is reviewed. Treat the table as a watchlist, not a contract.
| Date | Provider | Model or family | Replacement |
|---|---|---|---|
| 30 Nov 2026 | Anthropic | Claude Sonnet 4.5 | Claude Sonnet 5.5 |
| 11 Dec 2026 | OpenAI | GPT-5 family, o3, o3-pro | Current GPT-6 family |
| 14 Jan 2027 | OpenAI | GPT-4o, GPT-4o-mini, GPT-4.1 snapshots | GPT-6 family |
| 14 Jan 2027 | Azure OpenAI | GPT-4o 2024-05-13 | GPT-5.1 |
| 28 Jan 2027 | Google Vertex | gemini-3.7-flash | gemini-3.8-flash |
| 1 Apr 2027 | OpenAI | GPT-5.1, GPT-5.3-codex, GPT-5.4-nano | GPT-6 Sol / Luna |
| 8 Apr 2027 | AWS Bedrock | Claude Sonnet 4.5 | Current Claude on Bedrock |
| 30 Apr 2027 | Mistral | Mistral Large 3, Medium 3.5 | Mistral Large 4 |
Earlier 2026 dates, including OpenAI's 23 October batch and Google's 19 November Vertex retirement, are not repeated. Anthropic's 30 November date is still ahead.
Alias versus pinned model behavior
| Pattern | What moves | Best for | Risk |
|---|---|---|---|
latest alias | Points to the newest version | Prototypes, internal tools | Behaviour and price change without a deploy |
| Major alias | Newest minor within a generation | Teams that want fixes, not redesigns | Still moves under you |
| Pinned version | Nothing until retirement | Production, regulated workloads | You own every migration date |
| Dedicated deployment | Your capacity, your upgrade | Long-lived or custom models | Cost and operational burden |
Pin in production and float in development. Read GET /v1/models and store the returned model IDs in your deployment manifest; the endpoint is the live source of truth for what is available. A CI check that fails when a pinned ID disappears is cheaper than a 3 a.m. page. See the model catalogue.
# Fail deploys if a pinned model disappears from /v1/models
curl -s https://api.plugsky.com/v1/models \
-H "Authorization: Bearer $PLUGSKY_API_KEY" \
| jq -e '.data[] | select(.id == "plugsky-pro")' > /dev/null
# A non-zero exit blocks the deploy
Migration checklist
- Inventory. Search code, config, notebooks and cron jobs for every model ID and alias.
- Pin. Replace aliases with versioned IDs in production; record the retirement date.
- Baseline. Run 100–300 representative prompts and store outputs, token counts and latency.
- Evaluate. Run the same set on the replacement; compare quality, refusals, JSON validity and cost.
- Canary. Send 5–10% of traffic to the replacement with a rollback switch.
- Cut over. Move the rest, keep the old path for one retention window, then remove it.
- Record. Update the changelog, the runbook and the contract owner. Tell support what changed.
Do not migrate on the shutdown date. The last week is when the replacement is busiest and the least forgiving. A migration that starts 30 days before the date has room for an eval failure; one that starts the day before does not.
Changelog, RSS and monitoring
Plugsky publishes a changelog and an RSS feed at /feed.xml. The current documentation also references a model.deprecated webhook; the webhook section says platform event webhooks are on the roadmap, so confirm availability before you depend on it. Until then, poll GET /v1/models and watch the changelog.
For enterprise commitments, ask for the notice period, the notification address, the post-retirement behaviour and the dedicated-capacity option in writing. Those are contract terms, not documentation guarantees. See the docs for the current API behaviour and the comparisons for provider-by-provider differences.
FAQ
How much notice do AI providers give before retiring a model?
It ranges from about two weeks to twelve months. OpenAI gives at least six months for generally available models, Anthropic at least 60 days, and Mistral six months for GA models. AWS Bedrock, Google Vertex and Microsoft Foundry publish model-specific windows. Some providers publish no fixed period.
What happens when a model is retired?
Most providers reject requests to the retired model ID. Some, including Together AI and xAI, redirect an old ID to a replacement, which changes behaviour and price without a code change. Check the provider's documented behaviour rather than assuming an error.
Does Plugsky publish a model deprecation notice period?
Plugsky publishes a changelog and RSS feed, and the current docs describe model deprecations there. A separate public notice-period commitment is not stated in the pages reviewed on 20 November 2026. Enterprise notice terms should be verified in the contract.
How do I migrate to a replacement model safely?
Inventory every model ID, pin the current version, run a representative eval against the replacement, compare quality, latency and token counts, canary a small traffic slice, then cut over with a rollback path. Remove the old ID only after the retention window.
Sources
OpenAI deprecations page for notice periods and shutdown_date, checked 20 November 2026: developers.openai.com/api/docs/deprecations. Anthropic model deprecations for the 60-day floor, checked 20 November 2026: platform.claude.com/docs/en/about-claude/model-deprecations. AWS Bedrock model lifecycle for the 12-month, 6-month and 45-day windows, checked 20 November 2026: docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle.html. Mistral model lifecycle policy for GA and preview notice, checked 20 November 2026: docs.mistral.ai/inference/model-lifecycle.
Reviewed 20 November 2026. Notice periods and dates were checked against the providers' own pages on that date and can change. This page is not legal advice; enterprise notice, dedicated capacity and data-retention terms should be verified in the contract with counsel review.