Qwen3-ASR Flash
by Alibaba (China) · family qwen · listed Sep 2025
Speech transcription model for accurate audio-to-text and captioning workflows
Current rates USD per 1M tokens
Input$0.032
Output$0.032
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
qwen3-asr-flash- Context window
- 53K tokens
- Max output
- 4K tokens
- Input modalities
- audio
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- no
- Knowledge cutoff
- Apr 2024
- Released
- 2025-09-08
- Last updated
- 2025-09-08
← All Alibaba (China) listings