跳至主要內容

模型詳情

glm-4.5-air

由 GLM 提供
隨用隨付

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 size. GLM-4.5-Air also supports hybrid inference modes, offering a "thinking mode" for advanced reasoning and tool use, and a "non-thinking mode" for real-time interaction. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)

模型規格

上下文長度
最大輸出
輸入/輸出模態
發布日期
2025-07

02

API 端點

單一 MixRoute 閘道,OpenAI 相容

  • OpenAI-compatible /v1/chat/completions POST

03

價格

固定費率,單位:/1M Tokens

輸入

$0.2000 /1M Tokens

補全

$1.1000 /1M Tokens

快取讀取

$0.0300 /1M Tokens

08

Token 成本估算

基於本頁價格的即時估算,非實際帳單

同一前綴被重複讀取的輸入占比,最高 100%

單一端點,可驗證的決策

使用相同的請求格式測試此模型與替代路由

從真實工作負載開始,再由品質、總成本與故障條件決定是否導入正式環境流量。