zai
glm-5v-turbo
GLM-5V-Turbo is a multimodal coding foundation model optimized for agent workflows. Supports video, image, text, and file inputs with 200K context window and 128K max output. Features thinking mode, tool calling, context caching, and native multimodal fusion with CogViT vision encoder.
Provider:
zai
Model type:
chat
Location:
rest
Context Window
200000
Intelligence Rating
Speed Rating
Cost Efficiency Rating
Pricing
$
1.2
Input tokens per million
$
4
Output tokens per million
Features
Tool Calling
Supported
PDF Input
Supported
Vision
Supported
Reasoning
Supported
