GLM-4.5V

Z.ai's MoE visual reasoning model with 106B total and 12B active parameters. It accepts text, images, video and files, outputs up to 16K tokens, and handles document and GUI understanding.

Understands

text, images, video, documents

Produces

text

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.