Model detail
Qwen Audio
Audio understanding model for speech transcription, classification, and spoken content analysis.
AudioTextChinese
Model facts
Model IDqwen/qwen-audio
CompanyAlibaba
ContextAudio
Max output4K
InputAudio
OutputText
StatusPreview
Pricing
Input$0.12
Output$0.40
Cache read-
API entry
Endpoint/v1/chat/completions
Modelqwen/qwen-audio
SDKOpenAI-compatible