Model deprecation
Definition
Model deprecation is when an AI provider announces that a model or API will be retired and sets a date after which requests to it stop working. Until then it still runs, but users are expected to move to a recommended replacement.
By Ronan Liedmeier, fractional head of growth and course author · Published 17 October 2026 · Last updated 17 October 2026
Also called: model retirement, model shutdown
Any app, automation or script that names that model will break on that date if nobody acts. Providers replace models often, so handling deprecations is routine maintenance for anyone running AI in production.
How it works
Providers describe a similar lifecycle. Anthropic lists four states: active, legacy, deprecated and retired. A deprecated model "is still functional but no longer recommended," comes with a recommended replacement and a retirement date, and after retirement requests to it fail. OpenAI uses "deprecation" for the process of retiring a model or endpoint and "shutdown" for the day it stops being accessible.
Notice periods differ by provider and change over time. Each provider publishes its deprecation schedule and notice policy on a dedicated deprecations page, which is separate from the API reference most builders read.
Example
An agency runs a lead-scoring automation that calls one specific model. The provider deprecates it with a retirement date four months out. The agency had logged the model, SDK version and owner for each workflow, so they open a ticket, run a test set of past leads against the replacement, compare the scores, and switch well before the date.
Common mistake
Swapping in the replacement and shipping without re-testing. A newer model can format output differently or reject request settings the old one accepted. Run your golden dataset against the replacement first and treat the switch as a regression test.
Learn it in AI Academy
- Building on Moving APIsAdvanced · 12 min
Related terms
- Model pinning
- Model pinning is the practice of naming one exact, fixed model version in your code or settings, instead of a general name the provider can point at a newer model. It stops the model from changing under you before you have tested the new one.
- Regression testing for AI
- Regression testing for AI is re-running a fixed set of test cases after any change to a prompt or model, to check that what worked before still works. It catches changes that raise the average score while breaking one specific case.
- Golden dataset
- A golden dataset is a small, fixed set of real example inputs, each paired with an answer you know is right, used to test an AI system. You run every new prompt or model against it and compare the results with those known-good answers.
- API (application programming interface)
- An API (application programming interface) is a set of requests a software service agrees to accept from other programs, a bit like a menu. A program sends a request such as "create a contact" and the service sends back data or a confirmation.