Qwen3 Omni 30B A3B Instruct
The Qwen-Omni model accepts combined inputs of text and a single additional modality (image, audio, or video) to generate responses in text or speech.
text + image + audio + video → text + audio · made by Alibaba
$0.25→$0.97per Mtok in / out
Novita AI · 2 sellers
Sold by 2 ways
| Seller | Lane | Rate |
|---|---|---|
| Novita AI aggregator | standard | $0.25per Mtok in$0.97per Mtok outapi.novita.ai · read 2026-08-25 |
| PPIO aggregator | standard | $1.8per Mtok in$6.9per Mtok outapi.ppinfra.com · read 2026-09-16 |
About
Qwen3 Omni 30B A3B Instruct — a text and audio model from Alibaba, sold by 2 companies from $0.25 in and $0.97 out per million tokens.
It takes text, images, audio and video and returns text and audio, with a context window of 65,536 tokens. It was published in September 2025, trained on material up to April 2024. Its sellers say it can call a tool. The catalogue files it under speak. Two companies sell it. The cheapest is $0.25 in and $0.97 out per million tokens at Novita AI.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text + image + audio + video
- Returns
- text + audio
- Context
- 65,536 tokens
- Longest answer
- 16,384 tokens
- Published
- September 2025
- Knowledge to
- April 2024
- Parameters
- 30 billion · read from its own name, the total of a mixture
- Licence
- not read
- Sellers
- 2
- Maker's own price
- not read
- Price
- $0.25 in and $0.97 out per million tokens — Novita AI
Known as 1 name
qwen/qwen3-omni-30b-a3b-instruct