Qwen2.5 VL 72B Instruct
Qwen2.5 VL 72B Instruct is a vision-language model developed by Qwen that processes both text and image inputs. It is designed to analyze complex visual data, including charts, graphics, and layouts, alongside natural language tasks.
Qwen2.5 VL 72B Instruct specs and pricing
- Provider: Qwen
- Released: February 1, 2025
- Context window: 128K tokens
- Max output: 115K tokens
- Input: text, images
- Output: text
- Price: $0.80 input / $1.00 output per 1M tokens
What Qwen2.5 VL 72B Instruct is good at
- Analyzing data within charts and infographics
- Extracting information from document layouts and icons
- Identifying objects like plants and animals in images
To-dos to try with Qwen2.5 VL 72B Instruct
- Upload a screenshot of a complex business chart and ask for a summary of the key trends.
- Provide an image of a document layout and ask the model to extract the text and structure.
- Upload a photo of an insect and ask the model to identify the species.
FAQ
- What kind of visual information can this model process? The model is capable of analyzing text, charts, icons, graphics, and document layouts, as well as recognizing common objects like birds, fish, and plants.
- Who developed Qwen2.5 VL 72B Instruct? This model is developed and provided by Qwen.
- How much does Qwen2.5 VL 72B Instruct cost? Qwen2.5 VL 72B Instruct costs $0.80 per million input tokens and $1.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 2.38 credits ($1 = 100 credits).
- What is the context window of Qwen2.5 VL 72B Instruct? Qwen2.5 VL 72B Instruct can read up to 128K tokens at once and write up to 115K tokens in one reply.
- Can I use Qwen2.5 VL 72B Instruct without coding? Yes. In todo.is you pick Qwen2.5 VL 72B Instruct as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.