Skip to main content

GLM-4.5V (Non-reasoning)

Z AIGLMOpen WeightMIT · Commercial OK

Description

GLM-4.5V is a multimodal (vision-language) model based on GLM-4.5-Air (106B total, 12B active) that extends hybrid reasoning to images and video. It achieves state-of-the-art results across 40+ VLM benchmarks (image reasoning, video understanding, GUI tasks, chart/document parsing, grounding) while supporting a Thinking Mode switch for deep reasoning. Released under MIT with FP8/BF16 variants and tooling in Transformers, vLLM, and SGLang.

Release Date
2025-08-11
Parameters
108.0B
Context Length
64K
Modalities
image, text, video

Capability Radar

0
general
0
coding
0
reasoning
0
scienceest.
0
agents
90
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

No benchmark data available

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))

No category score data available

Pricing

Input Price$0.6 / 1M tokens
Output Price$1.8 / 1M tokens
Blended Price (3:1)$0.9 / 1M tokens
Cache Read Price$0.11 / 1M tokens
Cache Write PriceFree

Speed

Tokens/sec39.0
Time to First Token3.43s
Time to Answer3.43s

Provider Price Ranking

Provider Price Ranking

1 providers

ProviderInputOutput
1Z AIPRIMARY
$0.6
$1.8

Compare pricing across different API providers for this model.

External Sources