z-ai
Z.ai: GLM 4.5 Air
z-ai/glm-4.5-air
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Z.ai GLM-4.5 Air is a text-to-text mixture-of-experts model described by Z.ai as a compact member of the GLM-4.5 family for agent-oriented work. The model card reports 106 billion total parameters with 12 billion active, plus thinking and non-thinking modes. OpenRouter lists a 131,072-token context window, tool-calling controls, and a knowledge cutoff at the end of 2024. Z.ai reports competitive results, but the supplied evidence remains largely vendor- and catalog-reported.[1][2]
Strengths
- Z.ai reports a compact MoE design for this exact variant: 106B total and 12B active parameters.[1][2]
- The model card describes a thinking mode for complex reasoning and tool use, plus a non-thinking mode for immediate responses.[2]
- The model card says open GLM-4.5-Air releases use MIT terms and allow commercial use plus secondary development.[2]
Limitations
- Evidence consists of OpenRouter catalog data and Z.ai's own card; apart from category-specific Design Arena results, no broad independent evaluation, deployment requirements, or safety testing is supplied.[1][2]
- OpenRouter lists text-only input and output; no other modalities are evidenced.[1]
- The listed knowledge cutoff is 2024-12-31, so fresh facts may require retrieval or connected tools.[1]
Where to use it
- Agentic assistants that alternate direct answers with deeper reasoning and tool calls; test whether the two modes help the target workflow.[1][2]
- Design or front-end prototyping tasks such as code, data visualization, UI components, websites, SVG, or game-development experiments, based on OpenRouter's arena categories.[1]
- Long-document Q&A, summarization, or document analysis where the listed 131,072-token context window is useful.[1]
Sources
- [1] OpenRouter catalog · Z.ai: GLM 4.5 AirSources checked: Nov 13, 2026
- [2] Model documentation · Z.ai: GLM 4.5 AirSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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
- Creator
- z-ai
- Added to OpenRouter
- 25.07.2025
- Context length
- 131,072
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.200 / out $1.1
- Knowledge cutoff
- 31.12.2024
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | No measurement | — |
| Agents | No measurement | parameters: tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Design Arena | models · 3dwin rate 54.1% · rank 91 | 1,105Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 51.4% · rank 100 | 1,128Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 58.5% · rank 64 | 1,184Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 48.4% · rank 103 | 1,085Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · svgwin rate 50.8% · rank 77 | 1,063Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 54.4% · rank 96 | 1,114Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 51.3% · rank 100 | 1,139Elo | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Novitabf16 | 131,072 | $0.130 | $0.850 | — | — | 100% |
| SiliconFlowfp8 | 131,072 | $0.140 | $0.860 | — | — | 100% |
| Z.AIfp8 | 131,072 | $0.200 | $1.1 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.