DeepSeek V3.1 vs Z.ai GLM 4.5 Air
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- GLM 4.5 Air is 1.4× cheaper at a typical mix of 3 input tokens per output token.
- DeepSeek V3.1 accepts longer prompts: 164K vs 131K tokens.
| DeepSeek V3.1 | GLM 4.5 Air | |
|---|---|---|
| Vendor | DeepSeek | Z.ai |
| Released | 2025-08-21 | 2025-07-25 |
| Input / 1M | $0.25 | $0.13 |
| Output / 1M | $0.95 | $0.85 |
| Cached input / 1M | $0.13 | $0.025 |
| Blended / 1M (3:1) | $0.425 | $0.31 |
| Context | 164K | 131K |
| Max output | 147K | 98K |
| Accepts | text | text |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 5 | 3 |
| Cheapest provider, output | $0.95 | $0.85 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | — |
Cost calculator
DeepSeek V3.1
$29.25 per month$0.97 per day
GLM 4.5 Air
$20.55 per month$0.69 per day
GLM 4.5 Air saves $8.70 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare DeepSeek V3.1 with
Compare GLM 4.5 Air with