z-ai

Z.ai: GLM 4.5V

Z.ai: GLM 4.5V is an AI model capable of handling text and image inputs within a context length of 65,536 tokens, with robust support for reasoning and tools. This versatile model excels in understanding and generating both textual and visual content, making it suitable for a wide range of applications that require complex data processing. Considering its benchmark blended score of 10.0 across an independent set of evaluations, Z.ai: GLM 4.5V stands out as a reliable choice. However, with pricing at $0.6 per million input tokens and $1.8 per million output tokens, it might be more expensive for projects with higher token requirements or frequent use, though its performance justifies the cost for certain applications.

Quality Score
87/100
price + capability + benchmarks
Input Price
$0.60
per 1M tokens
Output Price
$1.80
per 1M tokens
Context Window
65,536
tokens

Benchmark results

Independent, published benchmarks. Blended score 10.0 across 1 benchmark, last refreshed 2026-07-25. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 11.5
Model ID
z-ai/glm-4.5v
Vendor
z-ai
Released
August 2025
Tokenizer
Other
Input Modalities
text, image
Output Modalities
text
Max Output
16,384 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
✓ accepts images
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.60/M input and $1.80/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.02
Classify 1,000 customer emails 500k in / 50k out $0.39
A month of a busy support chatbot 5M in / 2M out $6.60

Similar models

Quick answers

How much does Z.ai: GLM 4.5V cost?
$0.60 per million input tokens and $1.80 per million output tokens.
What is Z.ai: GLM 4.5V's context window?
65,536 tokens, roughly 98 pages of text in a single request.
Does Z.ai: GLM 4.5V support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can Z.ai: GLM 4.5V process images?
Yes, it accepts image input.