ONE MODEL, EVERY PLATFORM

`deepseek-v3.1` deprecation and shutdown dates on every platform

deepseek-v3.1 is tracked on 6 providers and hosting routes. First to go: Thinking Machines shuts down DeepSeek-V3.1 on Oct 23, 2026.

Last updated Oct 23, 2026

Thinking Machines

deepseek-v3.1 on Thinking Machines
Date	Model	Status	Replacement	Source
Oct 23, 2026	`DeepSeek-V3.1`	Shuts downToday	`DeepSeek-V4.1-Flash-1017`	Notice ↗

VertexGoogle Cloud Vertex AI

deepseek-v3.1 on Vertex
Date	Model	Status	Replacement	Source
Oct 21, 2026	`deepseek-v3.1-maas`	Shut down	Alternative: `Self-deploy DeepSeek-V3.1 on Model Garden`	Notice ↗

Alibaba

deepseek-v3.1 on Alibaba
Date	Model	Status	Replacement	Source
Oct 10, 2026	`deepseek-v3.1`	Shut down	`qwen3.7-plus`	Notice ↗

NovitaAI

deepseek-v3.1 on NovitaAI
Date	Model	Status	Replacement	Source
Sep 29, 2026	`deepseek/deepseek-v3.1`	Shut down	`deepseek/deepseek-v4.1-flash`	Notice ↗

AzureMicrosoft Azure / Foundry

deepseek-v3.1 on Azure
Date	Model	Status	Replacement	Source
Jul 13, 2026	`DeepSeek-V3.1@1`	Shut down	`DeepSeek-V4-Flash`	Notice ↗

Together AI

deepseek-v3.1 on Together AI
Date	Model	Status	Replacement	Source
May 14, 2026	`deepseek-ai/DeepSeek-V3.1`	Shut down	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.