GLM-4.5 Air
GLM-4.5 Air is Zhipu AI's language model with a 131K context window and up to 98K output tokens, available from 7 providers, starting at $0.125 / 1M input and $0.45 / 1M output. A compact MoE variant of GLM-4.5 from Z AI, offering a lighter architecture while retaining strong agentic reasoning and tool-use performance.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities7/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill✓
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
| $0.22 | $0.88 | N/A | |
| $0.13 | $0.85 | N/A | |
| $0.13 | $0.85 | N/A | |
| $0.13 | $0.85 | $0.025 | |
| $0.125 | $0.45 | N/A | |
| $0.2 | $1.10 | $0.03 | |
| $0.2 | $1.10 | N/A | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host GLM-4.5 Air, ranked by cheapest on-demand price. The model needs about 265 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| g7e.24xlarge |  AWS | 4× RTX PRO Server 6000 | 384 GB | $16.57/hr | us-east-1 | |
| g4-standard-192 |  GCP | 4× nvidia-rtx-pro-6000 | 384 GB | $18.00/hr | us-central1 | |
| p4d.24xlarge | AWS | 8× A100 | 320 GB | $21.96/hr | us-west-2 | |
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| GLM-4.7 | — | 205K | $0.400 | $1.75 | |
| GLM-4.6 | — | 205K | $0.431 | $2.00 | |
| GLM-4.5 | — | 131K | $0.400 | $1.60 |