Standard & Paid Price
Standard Price
| Meter | Standard Price |
|---|---|
| Input price | $0.2900 / 1M tokens |
| Completion price | $0.8800 / 1M tokens |
| Audio input price | $1.1500 / 1M tokens |
| Audio completion price | $2.3500 / 1M tokens |
Billing details
Description
Alibaba Qwen-Audio-3.0-Realtime-Flash — full-duplex speech-to-speech conversation over a WebSocket session, from the line the vendor reports as first overall in the Artificial Analysis Speech-to-Speech ranking. The flash tier is tuned for the lowest end-to-end response latency. Reached over GET /v1/realtime. Audio input and audio output are billed on their own faces, well above the text rate.
Capabilities
- Input modalities
- text, audio
- Output modalities
- text, audio
API endpoints
GET /v1/realtime(realtime)