z-ai/glm-4.5v
GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Novitafp8 | $0.600 | $1.80 | 66K | — |
| Z.AIfp8cache | $0.600 | $1.80 | 66K | — |
GLM 4.5V costs $0.600 per million input tokens and $1.80 per million output tokens via OpenRouter, making it 175th cheapest of 298 paid models.
GLM 4.5V scores 15.1 on the Artificial Analysis Intelligence Index, ranking 142nd of 178 benchmarked models, with a GPQA Diamond score of 68%.
GLM 4.5V generates around 43 tokens per second with 1.1s time-to-first-token (p50), the 195th fastest tracked model.
GLM 4.5V supports a 66K-token context window and can output up to 16K tokens. It accepts text, image input.