Qwen3-Omni Flash Realtime

Realtime voice Alibaba Qwen Partly verified Released Dec 4, 2025
  • In Input modalities: TextImageAudioVideo Out Output modalities: TextAudio

Prices

2 offerings · prices as listed
Alibaba Cloud Model Studio (opens in a new tab) Official International · USD qwen3-omni-flash-realtime
Conditions/ 1M tokensInputOutput
Text tokens no longer listed since Oct 11, 2026 $0.52—
Image tokens no longer listed since Oct 11, 2026 $0.94—
Audio tokens no longer listed since Oct 11, 2026 $4.57$18.13

Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Oct 10, 2026)

Alibaba Cloud Model Studio (opens in a new tab) Official China · CNY qwen3-omni-flash-realtime
Conditions/ 1M tokensInputOutput
Text tokens no longer listed since Oct 11, 2026 ¥2.20—
Image tokens no longer listed since Oct 11, 2026 ¥3.90—
Audio tokens no longer listed since Oct 11, 2026 ¥18.90¥75.10

Prices from 阿里云百炼:模型价格 (opens in a new tab) (checked Oct 4, 2026)

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

Details

Max input
49.15K
Max output
16.38K
Reasoning
—
Tool use
—
Languages
119
Knowledge cutoff
Apr 2024
Open weights
—
Model ID

Not stated on Alibaba Qwen’s pages: reasoning efforts, reasoning can be off, structured output, voices.

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. 2 prices dropped on Alibaba Cloud Model Studio, China Audio input ¥18.90 · Audio output ¥75.10

Sources

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

Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data

Alibaba Qwen · China · qwen.ai

Snapshots, the same family and other models from this provider