⚡️ 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 / Together AI
Embeddings

M2-BERT 80M 2K Retrieval

80M checkpoint of M2-BERT, pretrained with sequence length 2048, and it has been fine-tuned for long-context retrieval.

Request deployment
read docs

About model

M2-BERT 80M 2K Retrieval performs efficient text retrieval tasks, leveraging its key strength in semantic search. It is suited for applications requiring precise information retrieval. Designed for developers and researchers.

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

    Related models
    Embeddings
    GTE ModernBERT base
    • Input/1M
      $0.08
    • Parameters
      149.0M
    No items found.
    Embeddings
    Embeddings
    BGE-Base-EN v1.5
    • Input/1M
      $0.01
    • Parameters
      109M
    No items found.
    Embeddings
    Embeddings
    UAE-Large v1
    • Parameters
      326M
    No items found.
    Embeddings
    Model specifications
    Model data
    • Model provider
      Together AI
    • Type
      Embeddings
    • Main use cases
      Embeddings
    • Deployment
      Monthly Reserved
    • Parameters
      80M
    • Context length
      2048
    • Input modalities
      Text
    • Output modalities
      Structured Data
    • Category
      Embeddings
    Quickstart docs
    Deploy model