ModelInfo
English
All models

Qwen3-Omni-Flash-Realtime

Real-time omni-modal interaction over WebSocket.

Alibabaqwen3-omni-flash-realtimeReport incorrect data

Specs

Context
65.5K
Max output
16.4K
Input price
—
Output price
—
Released
—

Context

Context window
65.5K
Max input
49.2K
Max output
16.4K

Pricing

Not published

Modalities

Input
TextImageAudioVideo
Output
TextAudio

API

API types
realtime

Reasoning

Reasoning
No

Info

Status
Retired
Released
—
Knowledge cutoff
—

Features

Confirmed
streaming
Source · official docsVerified 2026-10-11

How to call

1 provider

alibabamodel = qwen3-omni-flash-realtime

JSON

Standard format
qwen3-omni-flash-realtime.json
{
  "id": "qwen3-omni-flash-realtime",
  "object": "model",
  "created": null,
  "owned_by": "alibaba",
  "name": "Qwen3-Omni-Flash-Realtime",
  "api": {
    "types": [
      "realtime"
    ]
  },
  "limits": {
    "context": 65536,
    "input": 49152,
    "output": 16384
  },
  "modalities": {
    "input": [
      "text",
      "image",
      "audio",
      "video"
    ],
    "output": [
      "text",
      "audio"
    ]
  },
  "reasoning": {
    "supported": false,
    "efforts": []
  },
  "pricing": null,
  "features": [
    "streaming"
  ],
  "info": {
    "status": "retired",
    "release_date": null,
    "knowledge_cutoff": null,
    "description": "Real-time omni-modal interaction over WebSocket.",
    "docs": "https://www.alibabacloud.com/help/en/model-studio/omni",
    "verified_at": "2026-10-11"
  }
}

Official sources

6