⚡️ 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 / Alibaba-NLP
Embeddings

GTE ModernBERT base

Text embedding and rerank models built on modernBERT, excelling in MTEB, LoCO, and COIR retrieval benchmarks.

Read the docs
read docs

About model

GTE ModernBERT base is a text embedding model developed by Tongyi Lab, Alibaba Group, providing competitive performance in text embedding and retrieval tasks, including MTEB, LoCO, and COIR evaluation, with a 149M parameter size and 768 output dimension.

To use this embeddings model, please follow the instructions from our Docs.

    Related models
    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
    Embeddings
    Multilingual e5 large instruct
    • Input/1M
      $0.02
    • Output/1M
      $0.02
    • Parameters
      559.9M
    No items found.
    Embeddings
    Model specifications
    Model data
    • Model provider
      Alibaba-NLP
    • Type
      Embeddings
    • Main use cases
      Embeddings
    • Deployment
      Monthly Reserved
    • Parameters
      149.0M
    • Input price

      $0.08 / 1M tokens

    • Input modalities
      Text
    • Output modalities
      Structured Data
    • Released
      January 19, 2025
    • Last updated
      February 24, 2026
    • External link
      Provider docs
    • Category
      Embeddings
    Quickstart docs
    Deploy model