⚡️ 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 / DeepSeek
Free
Chat
Reasoning

DeepSeek R1 Distilled Llama 70B Free

Free endpoint to experiment the power of reasoning models. This distilled model beats GPT-4o on math & matches o1-mini on coding.

Try our free DeepSeek R1 API
read docs

About model

DeepSeek R1 Distilled Llama 70B Free is a free-tier reasoning model distilled from DeepSeek R1, excelling in math, code, and logical reasoning. Suitable for developers and researchers exploring advanced reasoning at no cost.

    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
      DeepSeek
    • Type
      Free
      Chat
      Reasoning
    • Main use cases
      Chat
      Reasoning
    • Deployment
      On-Demand Dedicated
      Monthly Reserved
    • Parameters
      70B
    • Context length
      131K
    • Input modalities
      Text
    • Output modalities
      Text
    • Released
      January 20, 2025
    • Last updated
      November 12, 2025
    • External link
      Provider docs
    • Category
      Chat
    Quickstart docs
    Deploy model