ModelInfo
English
All models

Qwen-Audio-3.0-Realtime-Flash

Low-latency duplex speech model.

Alibabaqwen-audio-3.0-realtime-flash2026-07-14Report incorrect data

Specs

Context
41K
Max output
8.2K
Input price
—
Output price
—
Released
2026-07-14

Context

Context window
41K
Max input
16.4K
Max output
8.2K

Pricing

Not published

Modalities

Input
TextAudio
Output
TextAudio

API

API types
realtime

Reasoning

Reasoning
No

Info

Status
Active
Released
2026-07-14
Knowledge cutoff
—

Features

Confirmed
streaming
Source · official docsVerified 2026-10-11

How to call

1 provider

alibabamodel = qwen-audio-3.0-realtime-flash

JSON

Standard format
qwen-audio-3.0-realtime-flash.json
{
  "id": "qwen-audio-3.0-realtime-flash",
  "object": "model",
  "created": 1783987200,
  "owned_by": "alibaba",
  "name": "Qwen-Audio-3.0-Realtime-Flash",
  "api": {
    "types": [
      "realtime"
    ]
  },
  "limits": {
    "context": 40960,
    "input": 16384,
    "output": 8192
  },
  "modalities": {
    "input": [
      "text",
      "audio"
    ],
    "output": [
      "text",
      "audio"
    ]
  },
  "reasoning": {
    "supported": false,
    "efforts": []
  },
  "pricing": null,
  "features": [
    "streaming"
  ],
  "info": {
    "status": "active",
    "release_date": "2026-07-14",
    "knowledge_cutoff": null,
    "description": "Low-latency duplex speech model.",
    "docs": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
    "verified_at": "2026-10-11"
  }
}

Official sources

4