Model Library
Z AIReleased July 28, 2025GLM-4.5-Air
Z AI · Released July 28, 2025
Intelligence score
17
At a glance
- Intelligence
- 17
- Speed
- 65.3tokens/sec
- Latency
- 2.72stime to first token
- Input price
- $0.17per 1M tokens
- Output price
- $0.98per 1M tokens
- Context window
- 130Ktokens
- Parameters
- 106billions
Summary
Comparison summary
GLM-4.5-Air scores 17 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9). GLM-4.5-Air generates output at 65.3 tokens per second (based on the median across providers serving the model), which is below average compared to other open weight models of similar size (median: 88.2 t/s). GLM-4.5-Air costs $0.17 per 1M input tokens (better than average, median: $0.40) and $0.98 per 1M output tokens (somewhat higher than average, median: $0.84), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | GLM-4.5-Air |
|---|---|
| Provider | Z AI |
| Release date | July 28, 2025 |
| Intelligence score | 17 |
| Speed | 65.3 tokens/sec |
| Latency (TTFT) | 2.72s |
| Input price | $0.17 / 1M tokens |
| Output price | $0.98 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | 106B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | MIT |
| API availability | — |
| Source | Model Intelligence legacy profile: glm-4-5-air |
Pricing
Token prices
Price per 1M tokens
GLM-4.5-Air, as listed in the catalog record
- Input$0.17
- Output$0.98
| Token type | Price per 1M |
|---|---|
| Input | $0.17 |
| Output | $0.98 |
Model Intelligence legacy profile: glm-4-5-air
FAQ · 20
Frequently asked questions
GLM-4.5-Air was released on July 28, 2025.
GLM-4.5-Air was created by Z AI.
GLM-4.5-Air scores 17 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).
GLM-4.5-Air generates output at 65.3 tokens per second (based on the median across providers serving the model), which is below average compared to other open weight models of similar size (median: 88.2 t/s).
GLM-4.5-Air has a time to first token (TTFT) of 2.72s (based on the median across providers serving the model), which is at the higher end compared to other open weight models of similar size (median: 1.52s).
GLM-4.5-Air costs $0.17 per 1M input tokens (better than average, median: $0.40) and $0.98 per 1M output tokens (somewhat higher than average, median: $0.84), based on the median across providers serving the model.
GLM-4.5-Air costs $0.17 per 1M input tokens and $0.98 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.25 per 1M tokens. Pricing may vary by provider.
Yes, GLM-4.5-Air is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
GLM-4.5-Air supports text input.
GLM-4.5-Air supports text output.
No, GLM-4.5-Air does not support image input. It can only process text.
No, GLM-4.5-Air is not multimodal. It only supports text input.
GLM-4.5-Air has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, GLM-4.5-Air is open weights. The model weights are publicly available and can be downloaded for self-hosting.
GLM-4.5-Air has 106 billion parameters (12 billion active).
GLM-4.5-Air is a Mixture of Experts (MoE) model with 106 billion total parameters, but only 12 billion active parameters are used during inference.
GLM-4.5-Air is released under the MIT license. This license allows commercial use.
GLM-4.5-Air achieves a score of 17 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, GLM-4.5-Air is available via API through 2 providers.
GLM-4.5-Air is available through 2 API providers.