z-ai/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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Io Netfp8 | $0.125 | $0.850 | 131K | 100% |
| Novitabf16 | $0.130 | $0.850 | 131K | 100% |
| SiliconFlowfp8 | $0.140 | $0.860 | 131K | 100% |
| Z.AIfp8 | $0.200 | $1.10 | 131K | 98.9% |
GLM 4.5 Air costs $0.125 per million input tokens and $0.850 per million output tokens via OpenRouter, making it 68th cheapest of 298 paid models.
GLM 4.5 Air scores 23.2 on the Artificial Analysis Intelligence Index, ranking 107th of 178 benchmarked models, with a GPQA Diamond score of 73%.
GLM 4.5 Air generates around 48 tokens per second with 760ms time-to-first-token (p50), the 176th fastest tracked model.
GLM 4.5 Air supports a 131K-token context window and can output up to 131K tokens. It accepts text input.