Qwen Omni Turbo
Alibaba Cloud
🧠 Language Model
Multimodal model supporting text, image, audio input and text/audio output. Supports 49 voices for speech synthesis.
⏹ Retired on 2026-10-10
Specifications
Input modalitiestext, image, audio
Output modalitiestext, audio
Relative speed●●●●○ Fast
Deprecated on2026-07-10
Sunset on2026-10-10
Context window32,768 tokens
Max output8,192 tokens
Vision inputYes
Input price$0.1225 / 1M
Output price$0.4725 / 1M
Pricing
$0.1225 / 1M input tokens · $0.4725 / 1M output tokens
Platform credit pricing — live rates on the Models page.