/

/

GLM 5.3 FlashX

GLM 5.3 FlashX

このモデルについて

TEXT / LLM · テキスト / LLM

Z.ai | 1,048,576 token context | $0.37/M input, $1.25/M output. 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...