Qwen-VL-Max is a large-scale visual language model of the Qwen series. Compared to the Plus version, it further enhances visual reasoning capabilities and instruction-following abilities, offering higher levels of visual perception and cognition. It delivers optimal performance on more complex tasks.This model version is functionally equivalent to the snapshot model qwen-vl-max-2025-08-13.
Inference Service Provider
The inference service provider for qwen-vl-max is Alibaba Cloud Model Studio.
Model Capabilities
- China (Beijing)
- Singapore
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text Image Video | Output Modality | Text |
Model Experience | Supported | Function Calling | Unsupported |
Structured Outputs | Supported | Web Search | Unsupported |
Prefix Completion | Supported | Context Caching | Supported |
Batch Inference | Supported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 129024 | Max Output Length | 8192 |
Context Window | 131072 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
- Singapore
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 0.229 | Per 1M tokens |
Output | 0.573 | Per 1M tokens |
Input(Implicit Cache) | 0.046 | Per 1M tokens |
Input(Batch File) | 0.115 | Per 1M tokens |
Output(Batch File) | 0.287 | Per 1M tokens |
Rate Limits
- China (Beijing)
- Singapore
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 1200 |
TPM (Tokens Per Minute) | 1,000,000 |