GLM-5.3 Lands: Z.ai's Coding Model Drops the Off Switch on Thinking

Thu, 20 Aug 2026 09:00:00 +0530

Z.ai pushed GLM-5.3 live this week, and the interesting part is not the model weights, it is what the release quietly removes from the API surface. GLM-5.3 reuses the GLM-5.2 base model unchanged and gets every reported gain from post-training alone, which is itself a useful data point: a lab treating post-training as a first-class lever rather than a consolation prize while everyone waits for the next pretraining run. But the change that actually touches your code is smaller and easy to miss in the changelog. GLM-5.3 no longer accepts a disabled thinking mode. Send thinking: { type: "disabled" } and the request fails outright instead of quietly falling back to a non-reasoning response.

Glm on Kuldeep Pisda

GLM-5.3 Lands: Z.ai's Coding Model Drops the Off Switch on Thinking