S CostSaver
Sign in

GLM 5.3 FlashX

LLM

by z-ai · z-ai-glm-53-flashx-20260918

Context window

1.0M

Max output

131K

Providers

1

Best input

$0.37

About this model

GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...

Providers & prices

Provider Input $/MTok Output $/MTok Context
ZA Z.AI $0.37 $1.25 1.0M