DeepSeek-V4-Flash vs GLM 4.5 Air
DeepSeek vs Zhipu AI — benchmarks, pricing, and capabilities side by side.
- •DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 70.4)
- •DeepSeek-V4-Flash is cheaper ($0.10 vs $0.13 per 1M input)
- •DeepSeek-V4-Flash is faster
- •DeepSeek-V4-Flash has a larger context window (1M)
| DeepSeek-V4-Flash | GLM 4.5 Air | |
|---|---|---|
| Intelligence index | 89.4 | 70.4 |
| Developer | DeepSeek | Zhipu AI |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 1,048,576 tokens | 131,072 tokens |
| Input price | $0.10 / 1M | $0.13 / 1M |
| Output price | $0.20 / 1M | $0.85 / 1M |
| Speed | 109 tok/s | 63 tok/s |
| Released | April 24, 2026 | July 25, 2025 |
| Parameters | 284B (13B active) | — |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
DeepSeek-V4-Flash
GLM 4.5 Air
GPQA Diamond
89.4
75
Humanity’s Last Exam
32.1
10.6