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.