GLM-4.5-Flash by Zhipu AI — Specs, Pricing & Capabilities | whichllm

Model ID glm-4.5-flash

Provider Zhipu AI

Family glm-flash

Status -

Knowledge Cutoff 2025-04

Release Date 2025-07-28

Input Modalities text

Output Modalities text

Context Window 131072

Input Limit -

Output Limit 98304

Tool Calling Yes

Reasoning Yes

Structured Output -

Temperature Control Yes

Open Weights Yes

Input Cost / 1M tokens -

Output Cost / 1M tokens -

Reasoning Cost / 1M tokens -

Cache Read Cost / 1M tokens $0.00

Cache Write Cost / 1M tokens $0.00