Z.ai · Released Jul 25, 2025
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...
- Released
- Jul 25 2025
- Context window
- 131K 98K out
- Input / 1M tokens
- $0.13 from $0.10
- Output / 1M tokens
- $0.85 from $0.29
Where to run it
18 providers compared
Cheapest: ZenMux at $0.12 / $0.29 per 1M input / output tokens — 62% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| ZenMux | $0.12 | $0.29 | $0.023 | 128K | 96K | — | Cheapest |
| submodel | $0.10 | $0.50 | — | 131K | 131K | — | +25% |
| NanoGPT | $0.12 | $0.80 | $0.06 | 128K | 98K | — | +81% |
| NovitaBF16 | $0.13 | $0.85 | $0.025 | 131K | 98K | 100%24h | +93% |
| Kilo Gateway | $0.13 | $0.85 | $0.025 | 131K | 98K | — | +93% |
| LLM Gateway | $0.13 | $0.85 | $0.025 | 131K | 96K | — | +93% |
| Novita AI | $0.13 | $0.85 | $0.025 | 131K | 98K | — | +93% |
| Hugging Face | $0.13 | $0.85 | — | 131K | 98K | — | +93% |
| Zhipu AI | $0.12 | $0.90 | $0.024 | 131K | 98K | — | +96% |
| SiliconFlowFP8 | $0.14 | $0.86 | — | 131K | 118K | 99.3%24h | +99% |
| SiliconFlow (China) | $0.15 | $0.90 | — | 131K | 131K | — | +109% |
| Z.AIFP8 | $0.20 | $1.10 | $0.03 | 131K | 98K | 99.9%24h | +165% |
| Vercel AI Gateway | $0.20 | $1.10 | $0.03 | 128K | 96K | — | +165% |
| Tempr Gateway | $0.20 | $1.10 | $0.03 | 131K | 98K | — | +165% |
| DevPass (LLM Gateway) | $0.20 | $1.10 | $0.03 | 131K | 98K | — | +165% |
| Merge Gateway | $0.20 | $1.10 | $0.03 | 128K | 98K | — | +165% |
| Impossibl | $0.20 | $1.10 | $0.03 | 131K | 98K | — | +165% |
| OrcaRouter | $0.20 | $1.10 | $0.03 | 131K | 98K | — | +165% |
Value
Price vs. performance
GLM 4.5 Air Other Z.ai Other labs Value frontier · GSO vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
2 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| GSOSoftware engineering · Optimize real code to make it significantly faster | 2.9% | #22of 27 | Claude Fable 5.188.2% |
| Humanity's Last ExamReasoning & knowledge · Expert questions across 100+ subjects | 8.1% | #25of 32 | GPT-6 Astra54.8% |
Specs
Details
- Model ID
z-ai/glm-4.5-air- Developer
- Z.ai
- Release date
- Jul 25, 2025 ·
- Context window
- 131,072 tokens
- Max output
- 98,304 tokens
- API price
- $0.13 / $0.85 per 1M input / output tokens
- Providers
- 18
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.