Qwen2.5 VL 72B Instruct
Qwen2.5 VL 72B Instruct is a large language model made by Qwen, added to the catalog on 1 Feb 2025. It has a context window of 128,000 tokens and costs $0.80 per 1M input tokens and $1.00 per 1M output tokens. It accepts text and images and produces text. Typical uses: identify objects in images efficiently, analyze complex graphics and layouts and generate detailed textual analysis.
Price checked ยท source: OpenRouter
What Qwen2.5 VL 72B Instruct is
Introducing Qwen2.5 VL 72B Instruct by Qwen, released in February 2025. This model excels in processing both text and image inputs, making it versatile for various applications. With a substantial context length of 32,768 tokens, it can handle extensive data inputs, providing detailed text outputs. It is particularly adept at recognizing objects such as flowers, birds, fish, and insects, and can analyze complex elements like charts and graphics within images. This capability makes it a valuable tool for tasks that require detailed visual and textual analysis.
Key features
- Processes text and image inputs
- Outputs detailed text responses
- Recognizes common objects
- Analyzes charts and graphics
- Handles large context windows
- Supports various text parameters
Typical uses
- Identify objects in images efficiently
- Analyze complex graphics and layouts
- Generate detailed textual analysis
- Process large volumes of text data
- Enhance visual content understanding
Qwen2.5 VL 72B Instruct pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.80 |
| Output, per 1M tokens | $1.00 |
| Cached input read, per 1M tokens | $0.40 |
No price change since it was added on 1 Feb 2025.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0007 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.021 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.026 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.122 |
Qwen2.5 VL 72B Instruct specifications
| Model id | qwen/qwen2.5-vl-72b-instruct |
|---|---|
| Version | qwen2.5-vl-72b-instruct |
| Context window | 128,000 tokensAbout 96,000 English words |
| Max output | 115,200 tokens |
| Knowledge cutoff | 2024-06-30 |
| Added to catalog | 1 Feb 2025 |
| Input types | text, image |
|---|---|
| Output types | text |
| Tool calling | No |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
Write a short essay
RUN20 Nov 2026Write 150 words on how AI might positively upend work, leisure and creativity
Artificial intelligence (AI) has the potential to positively upend work, leisure, and creativity in numerous ways. In the workplace, AI can automate repetitive and mundane tasks, allowing employees to focus on more complex and creative work. This can lead to increased productivity and job satisfaction. In leisure, AI can personalize entertainment and leisure activities, providing tailored recommendations and experiences. For example, AI-powered streaming services can suggest movies and TV shows based on a user's viewing history and preferences. In terms of creativity, AI can assist artists and designers in generating new ideas and concepts. AI can also be used to analyze and learn from existing creative works, providing insights and inspiration for new creations. Overall, AI has the potential to enhance and augment human capabilities, leading to new and exciting possibilities in work, leisure, and creativity. However, it is important to consider the ethical and social implications of AI and ensure that it is used in a responsible and beneficial manner.
Draw with code
RUN20 Nov 2026Generate an SVG of a pelican riding a bicycle.
Compare Qwen2.5 VL 72B Instruct
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.