ModelClockphi-4-mini-instruct deprecation and shutdown dates on every platform
phi-4-mini-instruct is tracked on 2 providers and hosting routes. First to go: Azure (Microsoft Azure / Foundry) shuts down Phi-4-mini-instruct on Jan 17, 2027.
AzureMicrosoft Azure / Foundry
| Date | Model | Status | Replacement | Source |
|---|---|---|---|---|
Phi-4-mini-instruct | Shuts down86 days | microsoft--phi-4 (Foundry Managed Compute) | Notice ↗ |
CoreWeave
| Date | Model | Status | Replacement | Source |
|---|---|---|---|---|
microsoft/Phi-4-mini-instruct | Retired | JetBrains/Mellum2-12B-A2.5B-Instruct | Notice ↗ |
Every provider sets its own dates
A deadline on one platform says nothing about another: OpenAI, Azure, Amazon Bedrock, Google Vertex AI and model routers each retire their own copies on their own schedule. Snapshots of the same model (for example dated versions) are listed separately because each has its own date. Rows marked “No deprecation notice tracked” mean ModelClock has not seen a retirement notice for that route, not that one cannot exist.