⚡️ FlashAttention-4: up to 1.3× faster than cuDNN on NVIDIA Blackwell →

Introducing Together AI's new look →

🔎 ATLAS: runtime-learning accelerators delivering up to 4x faster LLM inference →

⚡ Together GPU Clusters: self-service NVIDIA GPUs, now generally available →

📦 Batch Inference API: Process billions of tokens at 50% lower cost for most models →

🪛 Fine-Tuning Platform Upgrades: Larger Models, Longer Contexts →

Models / Qwen
Chat
Vision

Qwen2.5-VL 72B Instruct

Vision-language model with advanced visual reasoning, video understanding, structured outputs, and agentic capabilities.

Try our Qwen2.5-VL API
read docs

About model

Qwen2.5-VL 72B Instruct analyzes images and texts, recognizing objects, charts, and graphics, and generates structured outputs, making it suitable for developers and applications requiring advanced vision-language understanding.

    Related models
    Vision
    Arcee AI Spotlight
    • Parameters
      8.29B
    JSON Mode
    Chat
    Vision
    Vision
    NIM Llama 3.2 11B Vision Instruct
    • Parameters
      11B
    • Deployment
      Dedicated Inference
    No items found.
    Vision
    Vision
    NIM Llama 3.2 90B Vision Instruct
    • Parameters
      90B
    • Deployment
      Dedicated Inference
    No items found.
    Vision
    Model specifications
    Model data
    • Model provider
      Qwen
    • Type
      Chat
      Vision
    • Main use cases
      Chat
      Vision
    • Features
      JSON Mode
    • Deployment
      On-Demand Dedicated
      Monthly Reserved
    • Parameters
      72B
    • Input price

      $1.95 / 1M tokens

    • Output price

      $8 / 1M tokens

    • Input modalities
      Text
      Image
    • Output modalities
      Text
    • Released
      January 26, 2025
    • Last updated
      January 4, 2026
    • External link
      Provider docs
    • Category
      Vision
    Quickstart docs
    Deploy model