⚡️ 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 Instant 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 / Meta
LLM

Llama 3.1 8B

Multilingual LLM pre-trained and instruction-tuned, surpassing open and closed models on key benchmarks.

Try our Llama 3.1 API
read docs

About model

Llama 3.1 8B generates human-like text based on input prompts, excelling at conversational dialogue and long-form content creation. It is designed for developers and businesses seeking advanced language capabilities.

    Related models
    new
    Chat
    MiniMax M2.5
    • Input/1M
      $0.30
    • Output/1M
      $1.20
    • Parameters
      228.7B
    Function Calling
    JSON Mode
    Reasoning
    Code
    new
    Chat
    GLM-5
    • Input/1M
      $1.00
    • Output/1M
      $3.20
    • Parameters
      744B
    Function Calling
    JSON Mode
    Chat
    Reasoning
    LLM
    New
    Chat
    Kimi K2.5
    • Input/1M
      $0.50
    • Output/1M
      $2.80
    • Parameters
      1T
    No items found.
    Chat
    Code
    LLM
    Model specifications
    Model data
    • Model provider
      Meta
    • Type
      LLM
    • Main use cases
      Chat
      Small & Fast
      Function Calling
    • Features
      Function Calling
      JSON Mode
    • Deployment
      On-Demand Dedicated
      Monthly Reserved
    • Parameters
      8B
    • Context length
      128K
    • Input price

      $0.18 / 1M tokens

    • Output price

      $0.18 / 1M tokens

    • Input modalities
      Text
    • Output modalities
      Text
    • Released
      July 22, 2024
    • Last updated
      March 5, 2026
    • Quantization level
      FP8
    • External link
      Provider docs
    • Category
      Chat
    Quickstart docs
    Deploy model