Primary use stated or inferred cautiously from official documentation.
Q
ALIBABA QWEN / qwen-audio-3.1-realtime-flash
Qwen Audio 3.1 Realtime Flash
A real-time duplex conversation model with text and audio input and output. It supports WebSocket, WebRTC and AOQ, tools and voice cloning; enable_thinking is not supported.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | qwen-audio-3.1-realtime-flash |
|---|---|
| Model type | Voice and audio |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 27 OCT 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text · Audio |
| Exit | Text · Audio |
| Context window | 262,144 tokens |
| maximum output | 16,384 tokens |
| Reasoning | Not published |
| Published tools | Features · Web search · Voice cloning |
| Structured Outings | Not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Not published |
| Verified platforms | Alibaba Cloud Model Studio |
Voice assistants with turn detection, continuous interaction and external tools, after validating permissions, quality and end-to-end latency.
Web search and functions cannot be enabled simultaneously. Maximum input is 245,760 tokens; audio history supports up to 50 turns and 300 seconds, not unlimited audio.
03 / CAPABILITIES
What it can do
Orientation
Voice assistants with turn detection, continuous interaction and external tools, after validating permissions, quality and end-to-end latency.
Context
262,144 tokens · 16,384 tokens
Tools and integration
Functions · Web search · Voice cloning
Access
Alibaba Cloud Model Studio
Input modalities
TextAudio
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | 0.23 USD / 1M text tokens | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | 0.70 USD / 1M text tokens | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Singapore, USD per million tokens: text input 0.23 and output 0.70; audio 0.93 and 1.87. When a response includes speech, its accompanying text has no separate charge. Beijing has separate rates; comparable numeric fields cover Singapore text only.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
No public scores specific to this Flash version have been verified. Qwen Audio 3.0 rankings and Plus variant results are not transferred.
i No verified scores for this checkpoint.
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
Qwen Audio 3.1 Realtime Flash
Version added to Inferama's verified catalog.
07 / SOURCES