Qwen3.5-Omni-Plus-Realtime
Qwen3.5-Omni-Plus-Realtime is a model by Alibaba for speech, it stands 6th of 16 on τ³-Voice Leaderboard, and one seller in the catalogue publishes a price for it.
text + image + audio + video → text + audio · made by Alibaba
$1.38→$8.25per Mtok in / out
Alibaba
Sold by 2 ways
| Seller | Lane | Rate |
|---|---|---|
| Alibaba api | china-beijing | $1.38per Mtok in$8.25per Mtok out$11per Mtok in, audio$41.26per Mtok out, audioalibabacloud.com · read 2026-08-25 |
| Alibaba api | singapore | $2.1per Mtok in$12.4per Mtok out$16.5per Mtok in, audio$62per Mtok out, audioalibabacloud.com · read 2026-08-25 |
Measured 1 standing
| Place | Board | Metric | Score |
|---|---|---|---|
| 6thof 16 | τ³-Voice Leaderboard | Pass^1 | 53.7 |
About
Qwen3.5-Omni-Plus-Realtime — a text and audio model from Alibaba, placed 6th of 16 on τ³-Voice Leaderboard.
It takes text, images, audio and video and returns text and audio. The catalogue files it under speak. It stands 6th of 16 on τ³-Voice Leaderboard.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text + image + audio + video
- Returns
- text + audio
- Boards
- 1
- Best place
- 6th of 16 — τ³-Voice Leaderboard
Known as 1 name
qwen3.5-omni-plus-realtime-2026-03-15