ONE MODEL, EVERY PLATFORM

`glm-5.2` deprecation and shutdown dates on every platform

glm-5.2 is tracked on 7 providers and hosting routes. No upcoming shutdown date is published. Most recently, Neuralwatt shut down glm-5.2 on Sep 16, 2026.

Last updated Oct 23, 2026

Neuralwatt

glm-5.2 on Neuralwatt
Date	Model	Status	Replacement	Source
Sep 16, 2026	`glm-5.2`	Removal date passed	`glm-5.3`	Notice ↗

IteraCompute

glm-5.2 on IteraCompute
Date	Model	Status	Replacement	Source
—	`GLM-5.2`	No deprecation notice tracked	None published	Notice ↗

Z.ai

glm-5.2 on Z.ai
Date	Model	Status	Replacement	Source
—	`GLM-5.2`	No deprecation notice tracked	None published	Notice ↗

Fireworks AI

glm-5.2 on Fireworks AI
Date	Model	Status	Replacement	Source
—	`GLM 5.2`	No deprecation notice tracked	None published	Notice ↗

Together AI

glm-5.2 on Together AI
Date	Model	Status	Replacement	Source
—	`zai-org/GLM-5.2`	No deprecation notice tracked	None published	Notice ↗

Friendli

glm-5.2 on Friendli
Date	Model	Status	Replacement	Source
—	`zai-org/GLM-5.2`	No deprecation notice tracked	None published	Notice ↗

Cloudflare Workers AI

glm-5.2 on Cloudflare Workers AI
Date	Model	Status	Replacement	Source
—	`cf/zai-org/glm-5.2`	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.