Qwen
Qwen-Omni Turbo
CTX33K
Real-time voice · Vision
TextImageAudioVideoInput$0.07/M
TextAudioOutput$0.27/M
Qwen omni model for text, vision, audio, and multimodal agent tasks
PaidProprietary472/1044
Qwen · Voice line
Qwen Omni
2 stages , from Qwen-Omni Turbo in Jan 2025 to Qwen2.5-Omni 7B in Dec 2024.
Evolution chamber01 / 02
Ready to evolve
Every generation. A new possibility.
Qwen-Omni Turbo · Jan 20252 stages, from Qwen-Omni Turbo (Jan 2025) to Qwen2.5-Omni 7B (Dec 2024). Press Evolve to watch each step.
How it grew
Context window
Max output
Output priceper 1M tokens, lower is better
Every stage
v1 Stage 1
QwenQwen-Omni Turbo
CTX33KReal-time voice · VisionTextImageAudioVideoInput$0.07/MTextAudioOutput$0.27/MQwen omni model for text, vision, audio, and multimodal agent tasks
PaidProprietary472/1044v2.5 Stage 2
QwenQwen2.5-Omni 7B
CTX33KReal-time voice · VisionTextImageAudioVideoInput$0.10/MTextAudioOutput$0.40/MQwen omni model for text, vision, audio, and multimodal agent tasks
Open weightsApache 2.0442/1044