Alibaba/ Qwen
Qwen3.7 Flash
alibaba/qwen/qwen3-7-flash
Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...
Released
2026-07-27
Context window
1M
Max output
66K
Weights
Closed
Modalities
Input
TextImageVideo
Output
Text
Identity
- Version
- qwen3.7-flash
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | qwen/qwen3.7-flash | openai_chat | 1M | 66K | TextImageVideo | Text | ReasoningNativeTool callNativeTemperatureNative | - | input $0.03/M · cache read $0.006/M output $0.13/M · cache write $0.038/M | Yes |
| CrossModel | qwen/qwen3.7-flash | openai_chat | 1M | 66K | TextImageVideo | Text | ReasoningNativeTool callNativeTemperatureNative | - | input $0.04/M · cache read $0.01/M output $0.13/M · cache write $0.04/M | Yes |
| Kilo Gateway | qwen/qwen3.7-flash | openai_chat | 1M | 66K | TextImageVideo | Text | ReasoningNativeTool callNativeTemperatureNative | - | input $0.03/M · cache read $0.006/M output $0.13/M · cache write $0.038/M | Yes |
Capabilities
ReasoningNativeTool callNativeTemperatureNative