Qwen Audio 3 Flash Realtime is Alibaba's language model, starting at $0.413 / 1M input and $4.13 / 1M output. A real-time audio language model in the Qwen3 family, optimized for low-latency streaming audio understanding and interaction.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
| $0.413 | $4.13 | $0.206 | $2.06 | |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Qwen Audio 3 Flash Realtime | — | — | $0.413 | $4.13 | Current |
| Qwen3.5 Omni Flash | — | — | $0.400 | $3.00 | Available |
| Qwen Flash Character | — | — | $0.050 | $0.400 | Available |
| Qwen TTS Flash | — | — | $0.230 | $1.43 | Available |
| Qwen3 ASR Flash | — | — | $0.000 | — | Available |
| Qwen3 ASR Flash Filetrans | — | — | $0.000 | — | Available |
| Qwen3 ASR Flash Realtime | — | — | $0.000 | — | Available |
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Qwen Audio 3 Plus Realtime | Plus | — | — | $0.688 | $5.50 |
| Qwen Audio 3 Plus TTS | Plus | — | — | — | — |
| EAGLE Qwen 2.5 3B Instruct | — | — | — | — | — |
| Qwen3.7 Plus | Plus | 1.0M | $0.320 | $1.28 | |
| Qwen3.7 Max | Max | 1.0M | $1.25 | $3.75 | |
| Qwen3.6 27B | — | 262K | $0.150 | $0.500 | |
| Qwen3.6 35B A3B | — | 262K | $0.140 | $0.450 | |
| Qwen3.6 Max Preview | Max | 262K | $1.04 | $6.24 | |
| Qwen3.6 Plus | Plus | 1.0M | $0.325 | $1.95 | |
| Qwen3 Max Thinking | Max | 262K | $0.780 | $3.90 |