GLM 4.5 Air
by Z.ai · z-ai/glm-4.5-air
GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...
- Input / 1M tokens
- $0.13
- Output / 1M tokens
- $0.85
- Context
- 131K
Specs
| Input price | $0.13 / 1M tokens |
|---|---|
| Output price | $0.85 / 1M tokens |
| Cached input | $0.025 / 1M tokens |
| Context window | 131K tokens |
| Max output | 98.3K tokens |
| Reads | text |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | Jul 25, 2025 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
3 providers serve this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Cache read / 1M | Uptime (30 min) | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Novita | bf16 | 131K | 98.3K | $0.13 | $0.85 | $0.025 | 100% | 1.58 s | 35 tok/s | Normal | |
| SiliconFlow | fp8 | 131K | 118K | $0.14 | $0.86 | — | 100% | 984 ms | 36 tok/s | Normal | |
| Z.AI | fp8 | 131K | 98.3K | $0.20 | $1.10 | $0.03 | 100% | 626 ms | 35 tok/s | Normal |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Related models
- Z.ai
GLM 5.3 Flash
- Input
- $0.018
- Output
- $0.14
- Context
- 1.05M
- Z.ai
GLM 5.3
- Input
- $0.08
- Output
- $3.60
- Context
- 1.05M
- Z.ai
GLM 5.2
- Input
- $0.006
- Output
- $7.00
- Context
- 1.05M
- Z.ai
GLM 5.3 Prime
- Input
- $2.80
- Output
- $8.80
- Context
- 1M
- Z.ai
GLM 5.3 FlashX
- Input
- $0.37
- Output
- $1.25
- Context
- 1.05M
- Z.ai
GLM 5.3 Flash (batch)
- Input
- $0.05
- Output
- $0.18
- Context
- 1.05M