ModelClockminimax-m2.5 deprecation and shutdown dates on every platform
minimax-m2.5 is tracked on 6 providers and hosting routes. No upcoming shutdown date is published. Most recently, Nebius shut down MiniMaxAI/MiniMax-M2.5 on Aug 31, 2026.
Nebius
| Date | Model | Status | Replacement | Source |
|---|---|---|---|---|
MiniMaxAI/MiniMax-M2.5 | Shut down | MiniMaxAI/MiniMax-M3 | Notice ↗ |
CoreWeave
| Date | Model | Status | Replacement | Source |
|---|---|---|---|---|
MiniMaxAI/MiniMax-M2.5 | Retired | MiniMaxAI/MiniMax-M3 | Notice ↗ |
HPC-AI
| Date | Model | Status | Replacement | Source |
|---|---|---|---|---|
minimax/minimax-m2.5 | Shut down | None published | Notice ↗ |
Together AI
| Date | Model | Status | Replacement | Source |
|---|---|---|---|---|
MiniMaxAI/MiniMax-M2.5 | Retired | None published | Notice ↗ |
Friendli
| Date | Model | Status | Replacement | Source |
|---|---|---|---|---|
| — | MiniMaxAI/MiniMax-M2.5 | No deprecation notice tracked | None published | Notice ↗ |
MiniMax
| Date | Model | Status | Replacement | Source |
|---|---|---|---|---|
| — | MiniMax-M2.5 | No deprecation notice tracked | None published | 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.