ModelClock
ONE MODEL, EVERY PLATFORM

kimi-k2.5 deprecation and shutdown dates on every platform

kimi-k2.5 is tracked on 7 providers and hosting routes. First to go: Azure (Microsoft Azure / Foundry) shuts down Kimi-K2.5@1 on Jan 26, 2027.

Last updated

AzureMicrosoft Azure / Foundry

kimi-k2.5 on Azure
DateModelStatusReplacementSource
Kimi-K2.5@1Shuts down95 daysNone publishedNotice ↗

HPC-AI

kimi-k2.5 on HPC-AI
DateModelStatusReplacementSource
moonshotai/kimi-k2.5Shut downNone publishedNotice ↗

Together AI

kimi-k2.5 on Together AI
DateModelStatusReplacementSource
moonshotai/Kimi-K2.5Shut downmoonshotai/Kimi-K2.6Notice ↗

AssemblyAI

kimi-k2.5 on AssemblyAI
DateModelStatusReplacementSource
kimi-k2.5RetiredNone publishedNotice ↗

Thinking Machines

kimi-k2.5 on Thinking Machines
DateModelStatusReplacementSource
Kimi-K2.5Shut downKimi-K2.6Notice ↗

Fireworks AI

kimi-k2.5 on Fireworks AI
DateModelStatusReplacementSource
Kimi K2.5Removal date passedKimi K2.6Notice ↗

Nebius

kimi-k2.5 on Nebius
DateModelStatusReplacementSource
moonshotai/Kimi-K2.5Shut downNone publishedNotice ↗

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.