GLM 4.5Von Krater.ai

GLM-4.5V is a vision-language foundation model for multimodal agent applications.

Released August 11, 2025

Specifications

GLM 4.5V at a glance

Context

65.5K tokens

Max output

16.4K tokens

Input

Text, Image

Output

Text

Input price

$0.60 / 1M

Output price

$1.80 / 1M

Knowledge cutoff

2024-12-31

Image inputTool callingReasoning support

Capabilities

What it is good at

Catalog capabilities

  • Accepts image input
  • Generates text responses
  • Supports tool calling

Good for

Image understandingUse with toolsDeep analysis

FAQ

Questions about GLM 4.5V

Clear answers based on the model catalog and Krater access.

GLM 4.5V supports a context window of 65,536 tokens.

Use GLM 4.5V in your API

Connect with Krater's unified API.

API access

Ready to use GLM 4.5V?

Access leading models in one focused workspace.