GLM-4.6V 106B-A12B
GLM-4.6V 106B-A12B is an AI model published by Zhipu AI, released on 2025-12-08, for Multimodal model, with 108B parameters, and 128K context length, with a 40.07 score on LiveBench.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Model basics
Open source & experience
Official resources
API details
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | ¥1.00/ 1M tokens | ¥3.00/ 1M tokens |
| Image | - | ¥1.00/ 1M tokens | — |
| Type | TTL | Write | Read |
|---|---|---|---|
| Text | - | ¥0.0000/ 1M tokens | ¥0.500/ 1M tokens |
| Text | - | ¥0.0000/ 1M tokens Cache = write | — |
| Text | - | — | ¥0.500/ 1M tokens Cache = hit |
| Image | - | ¥0.0000/ 1M tokens Cache = write | — |
| Image | - | — | ¥0.500/ 1M tokens Cache = hit |
“—” means the modality is not billed in that direction, or the vendor has not published a price for it.
Benchmark Results
GLM-4.6V currently shows benchmark results led by LiveBench (111 / 117, score 40.07). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
Publisher
Model Overview
GLM-4.6V 106B-A12B is an AI model published by Zhipu AI, released on 2025-12-08, for Multimodal model, with 108B parameters, and 128K context length, with a 40.07 score on LiveBench.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
