Skip to content

Infrastructure & Compute

Model deprecation

Gradually ending support for a particular AI system or version.

Example

A provider announces that an older AI system endpoint will be retired.

Why people use it

It tells users and builders that an older AI version is being phased out.

What you'll hear

“When will this version stop being supported?”

What this means for you

Test a migration before a retired version becomes unavailable.

Can you control it?

No

No direct control. This describes a wider issue, concept or result rather than something you can simply switch on or off in a tool.

Common questions

Does a replacement AI system behave identically?
No. Features, results and costs can differ.
Does deprecation always mean immediate shutdown?
No. A provider may announce a transition period before access ends.
Can a saved request fail after retirement?
Yes. It may refer to an unavailable version or rely on features that changed.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice