PluelyPluelyDokumentasi

Model · Z.ai

Pluely × Z.ai: GLM 5.3 FlashX

Teks → TeksTanpa penyiapan · tanpa kunci API

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...

Cara kerja Z.ai: GLM 5.3 FlashX di Pluely

Model terkait