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...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.0000002 | $0.200 |
| completion | 0.0000011 | $1.10 |
| input_cache_read | 0.00000003 | $0.030 |
{
"temperature": 0.75,
"top_p": null,
"frequency_penalty": null
}