modelgrep
Z

Z.ai: GLM 4.5V

z-ai/glm-4.5v

142nd smartest of 178ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
15.1
142nd of 178
Design Elo
Speed
43
195th fastest
Latency
1.1s
first token
Input price
$0.600
175th cheapest
Context
66K
16K max out

How it compares

Smarter than20%
of all ranked models
Faster than34%
of all ranked models
Cheaper than41%
of all ranked models

Overview

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...

Benchmarks

independent · via OpenRouter
Artificial Analysis21th percentile
Intelligence Index
15.1
Coding Index
10.9
Agentic Index
10.9
GPQA Diamond
68%
Humanity's Last Exam
6%
SciCode
22%
Tau²-Bench (agentic)
23%

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Novitafp8$0.600$1.80
Z.AIfp8cache$0.600$1.80

Specifications

Context window66K
Max output16K
Knowledge cutoffDec 2024
Input modalitiestext, image
Output modalitiestext
Prompt cachingSupported
Cache read price$0.110/M
ModeratedNo

GLM 4.5V FAQ

How much does GLM 4.5V cost?

GLM 4.5V costs $0.600 per million input tokens and $1.80 per million output tokens via OpenRouter, making it 175th cheapest of 298 paid models.

How smart is GLM 4.5V?

GLM 4.5V scores 15.1 on the Artificial Analysis Intelligence Index, ranking 142nd of 178 benchmarked models, with a GPQA Diamond score of 68%.

How fast is GLM 4.5V?

GLM 4.5V generates around 43 tokens per second with 1.1s time-to-first-token (p50), the 195th fastest tracked model.

What is GLM 4.5V's context window?

GLM 4.5V supports a 66K-token context window and can output up to 16K tokens. It accepts text, image input.

Compare head-to-head