⚡️ 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 / Refuel
Chat

Refuel LLM-2

47B model optimized for data tasks such as classification, structured data extraction, and more.

Try our Refuel LLM-2 API
read docs

About model

Refuel LLM-2 automates data labeling and classification tasks with high accuracy, handling structured and unstructured data at scale. It excels at labeling large datasets. Ideal for machine learning teams building training datasets.

    Related models
    new
    Chat
    NVIDIA Nemotron 3 Super
    • Parameters
      120B
    • Deployment
      Dedicated Inference
    No items found.
    Code
    Chat
    new
    Chat
    MiniMax M2.5
    • Input/1M
      $0.30
    • Output/1M
      $1.20
    • Parameters
      228.7B
    Function Calling
    JSON Mode
    Reasoning
    Code
    New
    Chat
    Qwen3.5 9B
    • Input/1M
      $0.10
    • Output/1M
      $0.15
    • Parameters
      9B
    Function Calling
    JSON Mode
    Reasoning
    Vision
    Chat
    Model specifications
    Model data
    • Model provider
      Refuel
    • Type
      Chat
    • Deployment
      On-Demand Dedicated
      Monthly Reserved
    • Parameters
      47B
    • Context length
      16K
    • Input price

      $0.60 / 1M tokens

    • Output price

      $0.60 / 1M tokens

    • Input modalities
      Text
    • Output modalities
      Text
    • Released
      May 6, 2024
    • Last updated
      February 5, 2026
    • External link
      Provider docs
    • Category
      Chat
    Quickstart docs
    Deploy model