Qwen-Flash is the fastest and most cost-effective model in the Qwen series, designed for simple jobs. Qwen-Flash features flexible tiered pricing, resulting in more reasonable billing compared to Qwen-Turbo. Usage \| API reference \| Try online \| Thinking #### International If you select the International deployment scope, model inference compute resources are dynamically scheduled worldwide, excluding the Chinese mainland. Static data is stored in your selected region. Supported region: Singapore.
function_callinghttps://dashscope-intl.aliyuncs.com/compatible-mode/chat| Model | Context | Max out | Pricing |
|---|---|---|---|
| qwen-audio-3.0-asr-flash-filetrans | — | — | — |
| qwen-audio-3.0-asr-flash-streaming | — | — | — |
| qwen-audio-3.0-asr-flash | — | — | — |
| qwen-audio-3.0-realtime-flash | — | — | — |
| qwen-audio-3.0-realtime-plus | — | — | — |
| qwen-audio-3.0-tts-flash | — | — | — |
| qwen-audio-3.0-tts-plus | — | — | — |
| qwen-audio-3.1-asr-flash-filetrans | — | — | — |
| qwen-audio-3.1-asr-flash-message | — | — | — |
| qwen-audio-3.1-asr-flash-streaming | — | — | — |
| qwen-audio-3.1-asr-flash | — | — | — |
| qwen-audio-3.1-realtime-flash | — | — | — |
| qwen-audio-3.1-realtime-plus | — | — | — |
| qwen-audio-3.1-tts-flash | — | — | — |
| qwen-audio-3.1-tts-next | — | — | — |
| qwen-audio-3.1-tts-plus | — | — | — |
| qwen-flash-character | 8K | — | — |
| qwen-flash | 1M | 33K | — |
| qwen-image-2.0-pro | — | 6 | — |
| qwen-image-2.0 | — | 6 | — |
| qwen-image-2.1-pro | — | — | — |
| qwen-image-2.1-turbo | — | — | — |
| qwen-image-3.0-pro | — | 6 | — |
| qwen-image-3.0 | — | 6 | — |
| qwen-image-edit-max | — | 6 | — |
| qwen-image-edit-plus | — | 6 | — |
| qwen-image-edit | — | 1 | — |
| qwen-image-max | — | 1 | — |
| qwen-image-plus | — | 1 | — |
| qwen-image | — | 1 | — |
| qwen-long | 10M | — | — |
| qwen-max | 128K | — | — |
| qwen-mt-image-2.0 | — | — | — |
| qwen-mt-image | — | — | — |
| qwen-omni-turbo-realtime | — | — | — |
| qwen-omni-turbo | 32K | — | — |
| qwen-plus | 1M | — | — |
| qwen-tts-realtime | — | — | — |
| qwen-tts | — | — | — |
| qwen-turbo | 1M | — | — |
| qwen-voice-design | — | — | — |
| qwen-voice-enrollment | — | — | — |
| qwen-deep-research | 1M | 33K | $0.01$0.02 |
| qwen-vl-ocr | 38K | 8K | $0.07$0.16 |
| qwen-doc-turbo | 262K | 33K | $0.09$0.14 |
| qwen-mt-lite | 16K | — | $0.12$0.36 |
| qwen-mt-flash | 16K | — | $0.16$0.49 |
| qwen-mt-turbo | 16K | — | $0.16$0.49 |
| qwen-math-turbo | — | — | $0.29$0.86 |
| qwen-plus-character-ja | 32K | 512 | $0.5$1.4 |
| qwen-plus-character | 32K | 4K | $0.5$1.4 |
| qwen-math-plus | 4K | 3K | $0.57$1.72 |
| qwen-mt-plus | 16K | 8K | $2.46$7.37 |
/v1/models/alibaba/qwen-flashQwen-Flash is the fastest and most cost-effective model in the Qwen series, designed for simple jobs. Qwen-Flash features flexible tiered pricing, resulting in more reasonable billing compared to Qwen-Turbo. Usage \| API reference \| Try online \| Thinking #### International If you select the International deployment scope, model inference compute resources are dynamically scheduled worldwide, excluding the Chinese mainland. Static data is stored in your selected region. Supported region: Singapore.