GLM-4.5V is a multimodal (vision-language) model based on GLM-4.5-Air (106B total, 12B active) that extends hybrid reasoning to images and video. It achieves state-of-the-art results across 40+ VLM benchmarks (image reasoning, video understanding, GUI tasks, chart/document parsing, grounding) while supporting a Thinking Mode switch for deep reasoning. Released under MIT with FP8/BF16 variants and tooling in Transformers, vLLM, and SGLang.
发布日期2025年8月11日
参数规模108B
上下文长度128K
许可证MIT
知识截止—
Benchmarks
评测成绩
暂无评测数据。
Pricing
API 价格对比
| 服务商 | 输入价 | 输出价 | 上下文 | 吞吐(tok/s) | 延迟(s) | 函数调用 | 代码执行 | 联网搜索 |
|---|---|---|---|---|---|---|---|---|
| 302.AI | $0.29 | $0.86 | 64K | — | — | ✓ | ✗ | ✗ |
| LLM Gateway | $0.60 | $1.80 | 128K | — | — | ✓ | ✗ | ✗ |
| Z.AI | $0.60 | $1.80 | 64K | — | — | ✓ | ✗ | ✗ |
| Zhipu AI | $0.60 | $1.80 | 64K | — | — | ✓ | ✗ | ✗ |
价格单位：美元/百万 token，数据来自社区整理，仅供参考。