StepAudio 2.5 Realtime

{
  "id": "stepaudio-2.5-realtime",
  "object": "model",
  "created": null,
  "owned_by": "stepfun",
  "name": "StepAudio 2.5 Realtime",
  "api": {
    "types": [
      "realtime"
    ]
  },
  "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": 1.5,
    "output": 10,
    "cache_read": 0.3,
    "cache_write": null
  },
  "features": [],
  "info": {
    "status": "active",
    "release_date": null,
    "knowledge_cutoff": null,
    "description": "End-to-end speech-to-speech model served over a WebSocket Realtime API, replying with streaming audio and a text transcript.",
    "docs": "https://platform.stepfun.ai/docs/en/guides/models/stepaudio-2.5-realtime",
    "verified_at": "2026-10-11"
  }
}