Alibaba/ Qwen
Qwen Flash
alibaba/qwen/flash
Efficient Qwen model for fast chat, extraction, and high-volume workloads
Released
2025-07-28
Context window
1M
Max output
33K
Weights
Closed
Modalities
Input
Text
Output
Text
Identity
- Version
- qwen-flash
- Knowledge cutoff
- 2024-04
- Aliases
- Qwen Flash
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| LLM Gateway | qwen-flash | openai_chat | 1M | 33K | Text | Text | ReasoningTool callTemperature | - | input $0.05/M · cache read $0.01/M output $0.4/M · cache write $0.0625/M | Yes |
| 302.AI | qwen-flash | openai_chat | 1M | 33K | Text | Text | ReasoningTool callTemperature | - | input $0.022/M output $0.22/M | Yes |
| Alibaba | qwen-flash | custom | 1M | 33K | Text | Text | ReasoningTool callTemperature | - | input $0.05/M output $0.4/M | Yes |
| Alibaba (China) | qwen-flash | custom | 1M | 33K | Text | Text | ReasoningTool callTemperature | - | input $0.022/M output $0.216/M | Yes |
Capabilities
ReasoningTool callTemperature
Official price
input $0.05/M
output $0.4/M