GLM-4.5V is Z.AI's new generation of visual reasoning models based on the MOE architecture. With a total of 106B parameters and 12B activation parameters, it achieves SOTA performance among open-source VLMs of the same level in various benchmark tests, covering common tasks such as image, video, document understanding, and GUI tasks.
| Model | Context | Max out | Pricing |
|---|---|---|---|
| GLM-4.5-Flash | — | — | $0$0 |
| GLM-4.5-Air | — | — | $0.2$1.1 |
| GLM-4.5 | 128K | 96K | $0.6$2.2 |
| GLM-4.5V | — | 16K | $0.6$1.8 |
| GLM-4.5-AirX | — | — | $1.1$4.5 |
| GLM-4.5-X | — | — | $2.2$8.9 |
/v1/models/zai/glm-4.5v