Step Audio R1.5
用于深度声音理解和推理的音频模型，边思考边说话。
规格
- 上下文
- —
- 最大输出
- —
- 输入价
- $1.43/ 百万 Token
- 输出价
- $15/ 百万 Token
- 发布日期
- —
上下文
- 官方未公布
价格 · USD / 百万 Token
- 输入
- $1.43
- 输出
- $15
- 缓存读取
- $0.29
- 缓存写入
- —
输入输出
- 输入
- 音频文本
- 输出
- 音频文本
API
- 接口类型
思考
- 官方未公布
源信息
- 状态
- 可用
- 发布日期
- —
- 知识截止
- —
能力
- 官方未公布
调用方式
1 个 Provider
stepfunmodel = step-audio-r1.5
JSON
标准格式
{
"id": "step-audio-r1.5",
"object": "model",
"created": null,
"owned_by": "stepfun",
"name": "Step Audio R1.5",
"api": {
"types": [
"audio"
]
},
"limits": {
"context": null,
"input": null,
"output": null
},
"modalities": {
"input": [
"audio",
"text"
],
"output": [
"audio",
"text"
]
},
"reasoning": {
"supported": null,
"efforts": []
},
"pricing": {
"currency": "USD",
"unit": "1M_tokens",
"input": 1.43,
"output": 15,
"cache_read": 0.29,
"cache_write": null
},
"features": [],
"info": {
"status": "active",
"release_date": null,
"knowledge_cutoff": null,
"description": "Audio model for deep sound understanding and reasoning that thinks while speaking.",
"docs": "https://platform.stepfun.com/docs/zh/guides/models/audio",
"verified_at": "2026-10-11"
}
}官方来源
2