LLMSwaps

Which model each app runs today, and when it last changed

The one successor named anywhere in this register

The retirement schedule carries two dated rows for the hosted video model. The earlier one names its replacement, a later version of the same model. The second names none. This is the only place in the register where a retirement and a destination were published in the same sentence. As of 2026-09-22.

What has been announced, entry by entryFilled where the vendor has announced something in that column, hollow where it has not.What has been announced, entry by entryWhat Microsoft Foundry publishesWhat MicrosoftFoundry publishesWhat that leaves openWhat that leavesopenDoes a retirement name what followsDoes a retirement name what follows — What Microsoft Foundry publishes: Yes, for the earlier of two rowsDoes a retirement name what follows — What that leaves open: Within the same model family, not across makersWhat the successor actually isWhat the successor actually is — What Microsoft Foundry publishes: A later version of the same modelWhat the successor actually is — What that leaves open: A version bump rather than a different engineDoes the second row name oneDoes the second row name one — What Microsoft Foundry publishes: No replacement is named for itDoes the second row name one — What that leaves open: And its date is later than the firstIs the move performed for youIs the move performed for you — What Microsoft Foundry publishes: Not stated on the schedule pageIs the move performed for you — What that leaves open: A deployment names a version, so somebody must
Fig. 1 Filled where the vendor has announced something in that column, hollow where it has not.
What the schedule says about what follows each of its two dated rows. Recorded 2026-09-22.
What the page is askedWhat Microsoft Foundry publishesWhat that leaves open
Does a retirement name what followsYes, for the earlier of two rowsWithin the same model family, not across makers
What the successor actually isA later version of the same modelA version bump rather than a different engine
Does the second row name oneNo replacement is named for itAnd its date is later than the first
Is the move performed for youNot stated on the schedule pageA deployment names a version, so somebody must

Inclusion rule. Read from the retirement schedule table, restricted to the video rows. A successor mentioned in a launch announcement but not in the schedule does not fill a cell. Order. What the schedule states first, then what it leaves to the customer.

1A successor inside the same family is the easy case

Naming a later version of the same model is the least demanding form of this disclosure. Nobody had to choose between makers, and the behaviour a caller depends on is likely to be closer than it would be under any other move.

It is still the only one published here, which says more about the field than about this platform. Everywhere else the ending arrives without a destination, and a reader has to infer the obvious candidate and hope.

2The second row shows the pattern breaking immediately

The successor named for the first row is itself scheduled to retire, and its own row names nothing. So the chain runs one link and stops, which is a more honest picture of what a version successor buys than a single row would give.

A production reading only the first row would conclude that this platform manages succession. Reading both shows that it documents one step at a time, and that the step after the next one has not been written yet.

A succession chain that runs one link and stopsThe earlier of two dated rows names its replacement, a later version of the same model. That replacement carries its own retirement date and names nothing after it, so the documented chain is one step long.First versionRetires 15 July 2026,with the next versionnamed in the row.Successor namedSecond versionRetires 15 October2026. No replacementnamed beside it.Then nothingUnwrittenWhatever follows isnot on the schedulepage yet.Where the documented route endsA caller names a version explicitly, so every link in this chain is an edit somebody has tomake.
Fig. 2 Reading only the first row suggests succession is managed here; reading both shows one step documented at a time.

3Naming is not moving

Nothing on the schedule says the platform performs the change. A deployment names a version explicitly, which is what makes the retirement visible in the first place and also what guarantees somebody has to edit something.

That puts this entry in the same position as Amazon Bedrock, which states the point outright. The difference is that this one at least says where to go.

4Sources

Read from the model retirement schedule on learn.microsoft.com, 2026-09-22. The whole entry is on Microsoft Foundry, and the column it sits in is on Named replacement. Same column, other entries: Sora, Gemini API.