Alibaba/ Qwen
Qwen-VL Max
alibaba/qwen/vl-max
Qwen vision-language model for visual reasoning, documents, and agent tasks
Released
2024-04-08
Context window
131K
Max output
8.2K
Weights
Closed
Modalities
Input
TextImage
Output
Text
Identity
- Version
- qwen-vl-max
- Knowledge cutoff
- 2024-04
- Aliases
- Qwen-VL Max
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| Alibaba | qwen-vl-max | custom | 131K | 8.2K | TextImage | Text | Tool callTemperature | - | input $0.8/M output $3.2/M | Yes |
| Alibaba (China) | qwen-vl-max | custom | 131K | 8.2K | TextImage | Text | Tool callTemperature | - | input $0.23/M output $0.574/M | Yes |
Capabilities
Tool callTemperature
Official price
input $0.8/M
output $3.2/M