Qwen3.8 Omni Flash Realtime

Realtime voice Alibaba Qwen Verified Released Sep 21, 2026

Qwen3.8-Omni-Flash-Realtime is designed for live conversations involving audio and video. It supports multiple audio channels, video aggregation, and connections to remote MCP tools, allowing conversations to incorporate external information and actions. Summary written by AI Index from Alibaba Qwen’s own pages.

  • In Input modalities: TextImageAudioVideo Out Output modalities: TextAudio
  • Tool use

Prices

2 offerings · prices as listed
Alibaba Cloud Model Studio (opens in a new tab) Official International · USD qwen3.8-omni-flash-realtime
Conditions/ 1M tokensInputOutput
Standard $0.23—
Text tokens —$0.70
Audio tokens $0.93$1.87

Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Nov 9, 2026)

Alibaba Cloud Model Studio (opens in a new tab) Official China · CNY qwen3.8-omni-flash-realtime
Conditions/ 1M tokensInputOutput
Standard ¥1.50—
Text tokens —¥4.50
Audio tokens ¥6.00¥12.00

Prices from 阿里云百炼:模型价格 (opens in a new tab) (checked Nov 9, 2026)

Standard: the price a request with no conditions pays (the headline price elsewhere on the site).

Details

Max output
65.54K
Built-in tools
Remote MCP
Model ID

Not stated on Alibaba Qwen’s pages: max input, reasoning, reasoning efforts, reasoning can be off, structured output, voices, languages, knowledge cutoff.

Cited scores

From third-party leaderboards, not measured by us

No cited leaderboard covers realtime voice models yet. We will cite one when its license allows.

  1. New realtime voice model

Sources

Alibaba Qwen’s official policies: data use, privacy, terms →

Alibaba Qwen · China · qwen.ai

Snapshots, the same family and other models from this provider