⚡️ 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 / Mistral AI
LLM

Mistral

7.3B model surpassing Llama 2 13B, nearing CodeLlama 7B on code, with GQA for speed and SWA for efficient long-sequence handling.

Request deployment
read docs

About model

Mistral processes natural language inputs for text analysis. Its key strength lies in legacy compatibility. It is intended for users requiring reserved model functionality.

This model is currently only available for Monthly Reserved deployments. Please request a deployment to get started.

    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
      Mistral AI
    • Type
      LLM
    • Main use cases
      Chat
      Small & Fast
    • Deployment
      Monthly Reserved
    • Parameters
      7B
    • Context length
      8192
    • Input modalities
      Text
    • Output modalities
      Text
    • Quantization level
      FP16
    • Category
      Chat
    Quickstart docs
    Deploy model