ONE MODEL, EVERY PLATFORM

`qwen3-32b` deprecation and shutdown dates on every platform

qwen3-32b is tracked on 5 providers and hosting routes. No upcoming shutdown date is published. Most recently, Nebius shut down Qwen/Qwen3-32B on Aug 31, 2026.

Last updated Oct 23, 2026

Nebius

qwen3-32b on Nebius
Date	Model	Status	Replacement	Source
Aug 31, 2026	`Qwen/Qwen3-32B`	Shut down	`nvidia/Nemotron-35-Lightning`	Notice ↗

Together AI

qwen3-32b on Together AI
Date	Model	Status	Replacement	Source
Jul 29, 2026	`Qwen/Qwen3-32B`	Shut down	`Qwen/Qwen3.5-27B`	Notice ↗

NovitaAI

qwen3-32b on NovitaAI
Date	Model	Status	Replacement	Source
Jul 1, 2026	`qwen/qwen3-32b`	Shut down	`qwen/qwen3.6-27b`	Notice ↗

Thinking Machines

qwen3-32b on Thinking Machines
Date	Model	Status	Replacement	Source
Jun 12, 2026	`Qwen3-32B`	Shut down	`Qwen3.8-27B`	Notice ↗

AssemblyAI

qwen3-32b on AssemblyAI
Date	Model	Status	Replacement	Source
—	`qwen3-32B`	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.