Back to models
QVQ-Max
Flagship modelRecommended
QVQ model discovered from Alibaba Cloud Model Studio official documentation. Category: flagship. Capabilities: reasoning, vision.
| Context window | 131,072 tokens |
| Max output tokens | N/A |
| Max input tokens | 106,496 tokens |
Pricing
| Type | Input | Output |
|---|---|---|
| Standard | $1.15 / 1M tokens | $4.59 / 1M tokens |
Parameters
| Parameter | Default | Range |
|---|---|---|
| Temperature | 1 | 0 to 2 |
| Top P | 1 | 0 to 1 |
| Frequency penalty | 0 | -2 to 2 |
| Presence penalty | 0 | -2 to 2 |
| Max stop sequences | 4 | — |
Supported features
Capabilities
- Streaming
- Function Calling
- Json Mode
- Reasoning
- System Prompt
Endpoints
- Chat Completions
- Fine Tuning
- Vision
Use cases
- text-chat
- vision
- function-calling
- reasoning
Model specifications
| Model ID | qvq-max |
| Family | qvq |
| Access type | Api |
| Input modalities | text, image |
| Output modalities | text |