endueendue

Z.ai

GLM-5V Turbo

z-ai/glm-5v-turbo

GLM that reads images and video, for vision-based coding.

MultimodalImages, Text, Video → TextReady on endue
  • Images
  • Coding
  • Audio & video

Overview

Good for

Written by endue

  • Images
  • Coding
  • Audio & video

Not ideal for

From the model’s specs

Nothing in the specs rules out common agent work.

Capabilities

Tool useSupported
Structured outputNot supported
JSON modeSupported
ReasoningSupported
VisionSupported
Audio inputNot supported
Video inputSupported
File inputNot supported
Long contextSupported

Specifications

Model ID
z-ai/glm-5v-turbo
Family
GLM-5V
Context window
203K tokens
Input
Images, Text, Video
Output
Text