GLM-5.3-Flash
Z.ai (Zhipu AI)Thinking is always on — the generation prompt opens a thinking block unconditionally.
coreinference servingin GLM-5.3-FlashZ.ai
specific method · filed under inference & serving
Thinking is enabled unconditionally by default, rather than being selected as an optional mode.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See reasoning control for the methods filed beside it.
Also called always-on thinking block, always has thinking enabled.
2 quotes from 2 sources, one card per model, each opening with its strongest.
Thinking is always on — the generation prompt opens a thinking block unconditionally.
Kimi K3 always has thinking enabled, and will return `reasoning_content`.