GLM 4.5V

Zai

A visual reasoning model based on the MoE architecture with 106B total parameters and 12B active. Achieves state-of-the-art performance among open-source VLMs of its scale across image, video, document understanding, and GUI tasks. Features a flexible thinking mode toggle for balancing speed and reasoning depth. Excels at webpage code generation from screenshots, object detection, document parsing, and long video analysis.

Try Now

Capabilities

Thinking

Tool Use

Image Input

PDF Input

Technical Specifications

Context Window

64,000 tokens

Max Output

16,000 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.60

Non-Reasoning Output

$1.80

Cache Read Input

$0.11

Tool Costs (per 1K calls)

Web Search

$15

Code Execution

$0.19

Legacy

Made legacy on

Reason

Superseded by GLM 5

Recommended Replacement

GLM 5V Turbo