Qwen2.5-VL 72B Instruct
Vision-language model with advanced visual reasoning, video understanding, structured outputs, and agentic capabilities.
This model is not available on Together’s Serverless API.
- TypeChatVision
- Main use casesChatVision
- FeaturesJSON Mode
- Parameters72B
- Context length32K
- Input price
$1.95 / 1M tokens
- Output price
$8 / 1M tokens
- Input modalitiesTextImage
- Output modalitiesText
- ReleasedJanuary 26, 2025
- Last updatedJanuary 4, 2026
- External link
- CategoryVision
