Z.ai: GLM 4.5 Air
by Z.aiZ.ai: GLM 4.5 Air is a large language model from Z.ai. It costs $0.130 per million input tokens and $0.850 per million output tokens. Its context window is 131K tokens.
- Input / 1M tokens
- $0.130
- Output / 1M tokens
- $0.850
- Cached input / 1M
- $0.025
- Context window
- 131K
On repeated prefixes
tokens
Who serves it cheapest
3 hosts serve GLM 4.5 Air. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| NovitaCheapestbf16 | $0.130 | $0.850 | 131K | - | 99.7% |
| SiliconFlowfp8 | $0.140 | $0.860 | 131K | - | 100.0% |
| Z.AIfp8 | $0.200 | $1.10 | 131K | - | 99.5% |
The spread between Novita and Z.AI is 1.4× for identical weights. Quantization and context limits differ, so check both columns before switching.
About 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...
Specifications
| Model ID | z-ai/glm-4.5-air |
|---|---|
| Provider | Z.ai |
| Context window | 131K tokens |
| Max output | 98K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | 2024-12-31 |
| Open weights | Yes - zai-org/GLM-4.5-Air |
| Released | July 25, 2025 |
Cheaper alternatives
Models that cost less than GLM 4.5 Air while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Z.ai: GLM 4.5 Air cost?
$0.130 per million input tokens and $0.850 per million output tokens. Cached input reads cost $0.025 per million tokens.
What is the context window of Z.ai: GLM 4.5 Air?
131K tokens, with up to 98K tokens of output per request.
Which provider serves Z.ai: GLM 4.5 Air cheapest?
Novita at $0.130 per million input tokens - 1.4× cheaper than Z.AI, the most expensive of the 3 hosts serving it.
Confirm against the source: Z.ai official pricing.