Compare / head-to-head
GLM-4.5vsGLM-4.5-Air
GLM-4.5 leads 2 of 2 shared benchmarks. GLM-4.5-Air is 2.2x cheaper per token. Both offer a 128K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 0
GLM-4.5 leads
Cheaper per token
GLM-4.5-Air
2.2x cheaper, input + output
Larger context
Tie
both 128K tokens
Provider uptime (30d)
—
Z.ai
GLM-4.5-Air
Z.ai
text
Quality
Benchmark matrix
2 shared · 0 only GLM-4.5 · 0 only GLM-4.5-Air| Benchmark | GLM-4.5 | GLM-4.5-Air | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| AIME 2025 | 93.3% ↗matharena ⚠ | 83.3% ↗matharena ⚠ | +10 pt | GLM-4.5 |
| LMArena Elo | 1430.2 ↗ | 1383.6 ↗ | +46.6 | GLM-4.5 |
| Only GLM-4.5 reports · 0 | ||||
| GLM-4.5 reports nothing GLM-4.5-Air does not. | ||||
| Only GLM-4.5-Air reports · 0 | ||||
| GLM-4.5-Air reports nothing GLM-4.5 does not. | ||||
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is GLM-4.5 minus GLM-4.5-Air in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | GLM-4.5 | GLM-4.5-Air | Edge |
|---|---|---|---|
| Context window | 128K tokens | 128K tokens | Tie |
| Max output | 98K tokens | 98K tokens | Tie |
| Input price / 1M | $0.6 ↗ | $0.2 ↗ | GLM-4.5-Air |
| Output price / 1M | $2.2 ↗ | $1.1 ↗ | GLM-4.5-Air |
| Cached input / 1M | $0.11 ↗ | $0.03 ↗ | GLM-4.5-Air |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $2.8 | $1.3 | GLM-4.5-Air |
| Modalities | text | text | Tie |
| Released | — | — | — |
| Cited benchmark scores | 2 | 2 | — |
Reliability
Z.ai status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
GLM-4.5 vs …
Models sharing the most benchmarksMore matchups
GLM-4.5-Air vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GLM-4.5 and GLM-4.5-Air on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.