What happens when an AI model is deprecated, and how do you prepare?
The notice that a model will be switched off on a set date. Until then it still answers; after its retirement date, every request to it fails, so code must move to a newer model first.
beginner · Also called Model retirement, Deprecated model, Model lifecycle, End of life (EOL)
A model you call through an API is not yours to keep. Providers retire older models to free capacity for new ones, and a retired model's name stops working: the same request that worked yesterday returns an error. Deprecation is the warning before that day.
The stages
Names vary by provider, but the path is the same:
| Stage | What it means |
|---|---|
| Active | Supported and recommended |
| Legacy | No more updates; may be deprecated later |
| Deprecated | Still answers, but has a replacement and a retirement date |
| Retired (end of life) | Requests fail |
Anthropic gives at least 60 days' notice before retiring a publicly released model. Amazon Bedrock gives most models a 6-month Legacy period, some 45 days, and in that period a model that an account has not called for 15 days may stop working for it early. The same model can retire on different dates on different platforms: Claude's dates on Bedrock and Google Cloud are set by those platforms, not by Anthropic.
Why a swap is not a rename
Changing the model name in your code is the easy part. The new model may:
- Reject old parameters. Anthropic removed
temperature,top_pandtop_kin its October 2026 API version, so code that sets them gets a 400 error on new models. - Count tokens differently, so the same prompt costs more or less, and fits a context window differently.
- Answer differently. Better on average is not the same as better at your task: a prompt tuned for one model can lose accuracy on its successor.
That last point is why a migration needs an evaluation setEval SetThe list of test cases an LLM app is graded on after every change. Each case is an input and what a good answer must do, so a score going up or down shows whether the change helped.: a few hundred of your real requests with known good answers, run on both models before the switch.
How to stay ahead
- Know what you call. Export usage by API key and model, from the provider's console, and list every model name in your code and config.
- Keep the model name in one setting, not scattered through code, so a switch is one change.
- Watch the deprecation pages of each provider you use, and of each platform, since dates differ.
- Test the replacement early, with your evaluation set, as soon as the notice arrives, not in the last week.
- Plan for fine-tuned models. A model fine-tuned on a base model that retires has to be trained again on the new one; on Bedrock, Legacy models accept no new fine-tuning jobs.
Our Claude Sonnet 4.5 retirement article walks through one migration, and the model pages under prices list each model still on sale.
Sources