QVQ-72B-Preview overview
QVQ-72B-Preview by Alibaba Cloud
Discover QVQ-72B-Preview, an experimental multimodal AI model designed for enhanced visual reasoning capabilities with strong performance benchmarks.
QVQ-72B-Preview specs
- Developer
- Alibaba Cloud
- Input
- Text, Image
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Basic Information
- Release Date: December 25, 2024
- Model Type: Multimodal Language Model
Overview:
QVQ-72B-Preview is an experimental research model developed by the Qwen team, focusing on enhancing visual reasoning capabilities. This model integrates advanced multimodal processing to interpret and generate responses based on both text and visual inputs, making it particularly adept at solving complex problems that require understanding visual content.
Key Features:
- Multimodal Reasoning: Capable of processing and reasoning with both text and images, allowing for comprehensive understanding and interaction.
- High Parameter Count: Contains 72 billion parameters, enabling detailed and nuanced responses across various tasks.
- Performance Benchmarks: Achieved a score of 70.3% on the Multimodal Massive Multi-task Understanding (MMMU) benchmark, demonstrating strong performance in multidisciplinary tasks.
- Dynamic Input Handling: Supports single images, text prompts, and mathematical problems with visual components for diverse applications.
- Enhanced Visual Understanding: Excels in interpreting graphs, diagrams, and equations, making it suitable for educational and scientific contexts.
Intended Use:
QVQ-72B-Preview is designed for developers and researchers looking to implement advanced AI capabilities in applications such as educational tools, interactive learning environments, visual question answering systems, and automated content generation.
Language Support:
The model supports multiple languages including English and Chinese, enhancing its applicability in diverse linguistic contexts.
Architecture:
QVQ-72B-Preview employs a transformer-based architecture optimized for multimodal inputs. This architecture allows the model to efficiently process complex visual information alongside textual data.
Use cases
- educational platforms for teaching complex visual math and science problems
- interactive learning environments involving images and text
- automated grading and assessment tools for STEM subjects
- AI-powered scientific research assistants capable of multimodal data interpretation
- visual question answering systems in academic and industrial settings
- applications requiring integration of visual content with advanced text reasoning
Capabilities
- Function calling
- Streaming
- Structured outputs
QVQ-72B-Preview API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $1.81 | 1M tokens |
| Output | $5.42 | 1M tokens |
QVQ-72B-Preview is unlisted on AI/ML API. The rates apply to existing integrations; the models below are current alternatives.
Prices from the AI/ML API price list, checked on Nov 4, 2026.
QVQ-72B-Preview vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 QVQ-72B-Preview | $1.81 | $5.42 |
| Qwen3.8 Omni Flash | $0.15 | $0.47 |
| Qwen3.8-Flash | $0.16 | $0.47 |
| Qwen 3.8 27B | $0.4761 | $3.39 |
| Qwen3.8 Max Prime | $4.23 | $12.7 |
Models similar to QVQ-72B-Preview
Related articles
QVQ-72B-Preview FAQ
Does QVQ-72B-Preview support streaming?
Yes, QVQ-72B-Preview can stream responses as they are generated.
Does QVQ-72B-Preview support tool calling and structured outputs?
Yes, QVQ-72B-Preview supports both function calling and structured outputs.
Who created QVQ-72B-Preview?
QVQ-72B-Preview was built by Alibaba Cloud.