The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...
Modalities
TextAudio
輸入 / 輸出價格
￦4,388 / ￦17,550
1M
Context
12.8萬
發佈日期
2026年1月20日
Pricing
價格以 KRW 為單位。匯率或利潤變動會立即反映。
| 輸入 (prompt) | ￦4,388 / 1M |
| 輸出 (completion) | ￦17,550 / 1M |
| Cache read | ￦439 / 1M |
| Cache write | — |
1,000 個輸入 tokens 加上 1,000 個輸出 tokens 的費用約為 ￦21.94。