GLM-4.5-Air is a more compact variant of GLM-4.5 designed for efficient Agentic, Reasoning, and Coding (ARC) applications. It features 106 billion total parameters with 12 billion active parameters using MoE architecture. Like GLM-4.5, it is a hybrid reasoning model providing thinking mode for complex reasoning and tool usage, and non-thinking mode for immediate responses. Despite its compact design, GLM-4.5-Air delivers competitive performance with a score of 59.8 across 12 industry-standard benchmarks, ranking 6th overall while maintaining superior efficiency. It supports 128K context length and is released under MIT open-source license allowing commercial use.
发布日期2025年7月28日
参数规模106B
上下文长度131K
许可证MIT
知识截止—
Benchmarks
评测成绩
| 评测基准 | 类别 | 分数 | 来源 |
|---|---|---|---|
| MATH-500 | math reasoning | 98.1 | 来源 |
| AIME24 | math reasoning | 89.4 | 来源 |
| MMLU-Pro | language reasoning math general | 81.4 | 来源 |
| TAU-bench-Retail | reasoning communication | 77.9 | 来源 |
| BFCL-v3 | general reasoning | 76.4 | 来源 |
| GPQA | reasoning general | 75.0 | 来源 |
| LiveCodeBench | reasoning general code | 70.7 | 来源 |
| AA-Index | general | 64.8 | 来源 |
| TAU-bench-Airline | reasoning communication | 60.8 | 来源 |
| SWE-bench-Verified | reasoning frontend_development code | 57.6 | 来源 |
| SciCode | reasoning math physics chemistry code | 37.3 | 来源 |
| Terminal-Bench | reasoning code | 30.0 | 来源 |
| BrowseComp | reasoning search | 21.3 | 来源 |
| HLE | reasoning math | 10.6 | 来源 |
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 |
|---|---|---|---|---|---|---|---|---|
| Z.AI Coding Plan | $0.00 | $0.00 | 131K | — | — | ✓ | ✗ | ✗ |
| Zhipu AI Coding Plan | $0.00 | $0.00 | 131K | — | — | ✓ | ✗ | ✗ |
| 302.AI | $0.11 | $0.29 | 131K | — | — | ✓ | ✗ | ✗ |
| LLM Gateway | $0.13 | $0.85 | 131K | — | — | ✓ | ✗ | ✗ |
| Z.AI | $0.20 | $1.10 | 131K | — | — | ✓ | ✗ | ✗ |
| Zhipu AI | $0.20 | $1.10 | 131K | — | — | ✓ | ✗ | ✗ |
| Cortecs | $0.22 | $1.34 | 131K | — | — | ✓ | ✗ | ✗ |
价格单位：美元/百万 token，数据来自社区整理，仅供参考。