qwen-audio-3.1-realtime-plus

Updated at:

A real-time duplex speech model with text and audio input and output, function calling, web search, and voice cloning.

The inference service provider is Alibaba Cloud Model Studio. The default voice is longanqian_v3.1. For integration, supported voices, and parameters, see the real-time speech guide.

Enable web search with enable_search. Web search and Function Calling can be enabled together.

Context limits

ParameterLimit (tokens)
Context window262,144
Max input length245,760
Max output length16,384

Pricing and rate limits

Text-only responses are billed at the text output rate. For responses containing both text and audio, only audio output is billed; the accompanying text has no separate output charge.

WebSocket RPM counts connection requests, not model responses. There is no separate limit on concurrent connections.

China (Beijing)

Prices are per million tokens.

Model IDText inputAudio inputText outputAudio output
qwen-audio-3.1-realtime-plusCNY 5CNY 40CNY 40CNY 150

Rate limits: 60 RPM and 100,000 TPM.

Singapore

Prices are per million tokens.

Model IDText inputAudio inputText outputAudio output
qwen-audio-3.1-realtime-plusCNY 5.833CNY 46.667CNY 46.667CNY 175.002

Rate limits: 60 RPM and 100,000 TPM.

How to call the model