GLM-4.6V

Open weights Active Multimodal MoE glm-4-6v

Open 106B vision-language model with a 128K context and native multimodal function calling.

Released
Dec 8, 2025
Context window
131K tokens
Max output
Not disclosed
Parameters
106B 12B active
Input price
$0.30 per 1M
Output price
$0.90 per 1M

Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.

Pricing

Launch priceDec 8, 2025
$0.30 in / $0.90 out
Current price since Dec 8, 2025
$0.30 in / $0.90 out
Cached input $0.05 per 1M

Specifications

Developer
Z.ai (Zhipu AI)
Model type
Multimodal
Architecture
MoE
Parameters
106B (12B active)
Input
Text Image Video
Output
Text
Knowledge cutoff
Not disclosed
License
MIT License
API access
First-party API
Capabilities
Tool use Vision