⚡️ 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 / Google
Chat
Code
Vision

Gemma 3 1B

Most lightweight Gemma 3 model, with 128K context, vision-language input, and multilingual support for on-device AI.

Deploy Gemma 3 1B
read docs

About model

Gemma 3 1B generates human-like text based on input prompts, offering efficient language understanding in a compact 1B parameter footprint. Suitable for developers and researchers requiring lightweight language generation 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
    Qwen3.5 9B
    • Input/1M
      $0.10
    • Output/1M
      $0.15
    • Parameters
      9B
    Function Calling
    JSON Mode
    Reasoning
    Vision
    Chat
    new
    Chat
    GLM-5
    • Input/1M
      $1.00
    • Output/1M
      $3.20
    • Parameters
      744B
    Function Calling
    JSON Mode
    Chat
    Reasoning
    LLM
    Model specifications
    Model data
    • Model provider
      Google
    • Type
      Chat
      Code
      Vision
    • Main use cases
      Chat
      Small & Fast
    • Fine tuning
      Supported
    • Deployment
      On-Demand Dedicated
      Monthly Reserved
    • Parameters
      1B
    • Context length
      32K
    • Input modalities
      Text
    • Output modalities
      Text
    • Released
      March 10, 2025
    • Last updated
      September 9, 2025
    • External link
      Provider docs
    • Category
      Chat
    Quickstart docs
    Deploy model