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...

Details

FieldValue
idz-ai/glm-5.3-flashx
familyglm
modalitytext+image+video->text
context_length1048576
max_output_tokens131072
release_date2026-09-18
is_open_weightsno
supports_tool_callyes
supports_reasoningyes
supports_structured_outputno
supports_attachmentyes
input_modalitiestext, image, video
output_modalitiestext
Z.ai: GLM 5.3 FlashX