---
title: "What is model deprecation? LLM retirement dates and notice"
description: "Model deprecation is a provider's notice that a model will be retired on a set date. How OpenAI, Anthropic and Google handle notice periods, and how to prepare."
url: https://broadrouter.com/glossary/model-deprecation/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Model deprecation

Updated 2026-11-15

Model deprecation is when an API provider announces that a model will stop being offered, usually naming a retirement or shutdown date and a recommended replacement. After that date, requests to the model fail, so applications must migrate to another model ID beforehand.

Also called: model retirement, deprecated model, deprecation notice, model sunset, deprecation policy

Every hosted model has an end date, even if nobody has announced it yet. A deprecation notice is the start of the clock.

## How it works

Providers publish a lifecycle with named stages. Anthropic’s is the most detailed:

-   **Active:** fully supported and recommended.
-   **Legacy:** “will no longer receive updates and might be deprecated in the future.”
-   **Deprecated:** “still functional but no longer recommended”, with a replacement and a retirement date.
-   **Retired:** “no longer available for use. Requests to retired models fail.”

OpenAI uses two terms: deprecated, meaning “OpenAI has announced the model’s retirement”, and shutdown, when “The model no longer accepts requests through the standard API.”

Notice periods, as published on 15 November 2026:

| Provider | Stated notice | How customers hear |
| --- | --- | --- |
| OpenAI | At least 6 months for generally available models; at least 3 months for specialised and image generation models; preview models may go sooner | Email and the deprecations page |
| Anthropic | At least 60 days for publicly released models | Email and the documentation |
| Google (Vertex AI) | Standard models “available for at least 12 months after release”; short-term models get a retirement date that gives “at least 45 days to migrate”; dates “won’t be moved to an earlier date” | Fixed dates in a published table |

A real example: Anthropic notified Claude Sonnet 4.5 users on 30 September 2026 of retirement on 30 November 2026, with `claude-sonnet-5-5` as the replacement.

## Why it matters

-   **Silent breakage.** After the date, a hard-coded model ID returns errors. Keep model IDs in config, not code.
-   **Behaviour changes.** A replacement model answers differently. Anthropic advises testing “well before the retirement date”. Re-run your [eval](https://broadrouter.com/glossary/eval/) on the replacement, and see [evaluate an LLM before switching](https://broadrouter.com/blog/evaluate-llm-before-switching/).
-   **Cost and limits change too.** The replacement can have different prices, context length and rate limits.
-   **Audit usage.** Find every service and key that still calls the old model before the deadline.

## On BroadNet Inference

BroadNet does not publish a separate deprecation policy or fixed notice period. Its Terms of Service (§7.4) say BroadNet “may change, suspend or retire a model or feature and, where we can, give reasonable notice on the catalogue page”, and that self-serve has no availability commitment. BroadNet’s machine-readable `pricing.json` gives each model a `status` of `live` or `on_request`. Do not rely on `/v1/models` for this: BroadNet describes it as catalogue metadata for external monitors, and it does not list every chat model. Our post on [reading model status](https://broadrouter.com/blog/understand-model-status/) includes a status-checking script that you can run in CI to catch a model moving or disappearing. The [provider checklist](https://broadrouter.com/blog/choose-llm-api-provider-checklist/) suggests asking for notice terms in writing if they matter, and keeping a second provider for critical paths. BroadNet’s Terms describe its models as open-weight models or models trained by BroadNet. For an [open-weight](https://broadrouter.com/glossary/open-weight-model/) model, the weights stay available under their [licence](https://broadrouter.com/glossary/model-license/) even if BroadNet stops serving it.

## Questions

### What is the difference between deprecated and retired?

A deprecated model still works but has a planned end date. A retired or shut-down model no longer accepts requests. Anthropic adds a "legacy" stage before deprecation for models that no longer receive updates.

### How much notice do providers give?

It varies. OpenAI states at least 6 months for generally available models and at least 3 months for specialised variants. Anthropic states at least 60 days for publicly released models. Google lists standard Vertex AI models as available for at least 12 months after release; for short-term models it posts a retirement date at least 45 days ahead.

### Can an open-weight model be retired?

A provider can stop hosting it, but the weights stay available under their licence, so you or another host can keep serving the same model.

## See also

-   [Inference provider](https://broadrouter.com/glossary/inference-provider/) (term)
-   [Eval (LLM evaluation)](https://broadrouter.com/glossary/eval/) (term)
-   [Open-weight model](https://broadrouter.com/glossary/open-weight-model/) (term)
-   [SLA (service level agreement)](https://broadrouter.com/glossary/sla/) (term)
-   [Model fallback](https://broadrouter.com/glossary/model-fallback/) (term)
-   [Model license](https://broadrouter.com/glossary/model-license/) (term)
-   [Live, on request, research: read a model catalogue clearly](https://broadrouter.com/blog/understand-model-status/) (article)
-   [How to choose an LLM API provider: a 20-point checklist](https://broadrouter.com/blog/choose-llm-api-provider-checklist/) (article)
-   [How to evaluate an LLM before switching providers](https://broadrouter.com/blog/evaluate-llm-before-switching/) (article)

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=glossary-model-deprecation&utm_content=page-cta) ·

**Sources**

-   [OpenAI API docs, deprecations (checked 2026-11-15)](https://developers.openai.com/api/docs/deprecations)
-   [Anthropic, model deprecations (checked 2026-11-15)](https://platform.claude.com/docs/en/about-claude/model-deprecations)
-   [Google Cloud, Vertex AI model versions and lifecycle (checked 2026-11-15)](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions)
-   [BroadNet Terms of Service, §7.4 Availability (checked 2026-11-15)](https://www.broadnet.ai/terms)
