Qwen2.5 72B Instruct
Qwen2.5 72B Instruct is a large language model developed by Qwen. It is designed for text-based tasks with a focus on improved coding and general knowledge capabilities compared to previous versions.
Qwen2.5 72B Instruct specs and pricing
- Provider: Qwen
- Released: September 19, 2024
- Context window: 33K tokens
- Max output: 16K tokens
- Input: text
- Output: text
- Price: $0.36 input / $0.40 output per 1M tokens
- Tool calling: yes
What Qwen2.5 72B Instruct is good at
- Complex programming and software development tasks
- Generating detailed text-based content
- Applications requiring tool-calling functionality
To-dos to try with Qwen2.5 72B Instruct
- Write a Python script to automate data cleaning for a CSV file
- Draft a technical document explaining a specific coding architecture
- Use tool-calling to integrate the model into a custom software workflow
FAQ
- What is Qwen2.5 72B Instruct primarily designed for? It is designed for general language tasks with specific enhancements in coding proficiency and knowledge retrieval.
- Does this model support external tool integration? Yes, the model includes built-in support for tool-calling capabilities.
- How much does Qwen2.5 72B Instruct cost? Qwen2.5 72B Instruct costs $0.36 per million input tokens and $0.40 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.06 credits ($1 = 100 credits).
- What is the context window of Qwen2.5 72B Instruct? Qwen2.5 72B Instruct can read up to 33K tokens at once and write up to 16K tokens in one reply.
- Can I use Qwen2.5 72B Instruct without coding? Yes. In todo.is you pick Qwen2.5 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.