GL
Parameters
106B
Context length
64K
Multilingual
Supported
Reasoning ability
3/5
GLM-4.5V is an AI model published by Zhipu AI, released on 2025-08-11, for Multimodal model, with 106B parameters, and 64K context length, requiring about 312GB storage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
GLM-4.5V
Model basics
Reasoning traces
Supported
Thinking modes
Standard Mode (Default)Thinking Mode
Context length
64K tokens
Max output length
64K tokens
Model type
Multimodal model
Modality (in / out)
Text, Image, Video → Text
Release date
2025-08-11
Model file size
312GB
MoE architecture
Yes
Total params / Active params
106B / 12B
Knowledge cutoff
No data
GLM-4.5V
Open source & experience
GLM-4.5V
Official resources
Paper
DataLearnerAI blog
N/A
GLM-4.5V
API details
API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | ¥2.00/ 1M tokens | ¥6.00/ 1M tokens |
| Image | - | ¥2.00/ 1M tokens | — |
Cache PricingPrompt Cache
| Type | TTL | Write | Read |
|---|---|---|---|
| Text | - | ¥0.0000/ 1M tokens | ¥1.00/ 1M tokens |
| Text | - | ¥0.0000/ 1M tokens Cache = write | — |
| Text | - | — | ¥1.00/ 1M tokens Cache = hit |
| Image | - | ¥0.0000/ 1M tokens Cache = write | — |
| Image | - | — | ¥1.00/ 1M tokens Cache = hit |
“—” means the modality is not billed in that direction, or the vendor has not published a price for it.
GLM-4.5V
Publisher
Zhipu AI
View publisher details GLM-4.5V
Model Overview
GLM-4.5V is an AI model published by Zhipu AI, released on 2025-08-11, for Multimodal model, with 106B parameters, and 64K context length, requiring about 312GB storage.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
