⚡️ 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

Qwen QwQ-32B

Qwen series reasoning model excelling in complex tasks, outperforming conventional instruction-tuned models on hard problems.

Try our Qwen QwQ API
read docs

About model

QwQ-32B is a causal language model that excels in reasoning and problem-solving, achieving competitive performance against state-of-the-art models. It is suitable for users requiring advanced reasoning capabilities, particularly for hard problems.

    Related models
    Chat
    Gemma-4-31B-it-Pearl

    • Input/1M

      $0.28

    • Output/1M

      $0.86
    • Parameters
      31B
    Function Calling
    JSON Mode
    Reasoning
    new
    Chat
    GLM-5.1

    • Input/1M

      $1.40

    • Output/1M

      $4.40
    • Parameters
      754B
    Function Calling
    JSON Mode
    Reasoning
    Chat
    New
    Chat
    MiniMax M2.7

    • Cached/1M

      $0.06

    • Input/1M

      $0.30

    • Output/1M

      $1.20
    Function Calling
    JSON Mode
    Prompt Caching
    Reasoning
    Code
    Chat
    Model specifications
    Model data
    • Model provider
      Qwen
    • Type
      Chat
    • Main use cases
      Chat
      Reasoning
    • Features
      JSON Mode
    • Deployment
      On-Demand Dedicated
      Monthly Reserved
    • Parameters
      32B
    • Context length
      131,072
    • Input price

      $1.20 / 1M tokens

    • Output price

      $1.20 / 1M tokens

    • Input modalities
      Text
    • Output modalities
      Text
    Quickstart docs
    Deploy model