⚡️ 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 / Salesforce
Rerank

Salesforce LlamaRank

Salesforce Research's proprietary fine-tuned rerank model with 8K context, outperforming Cohere Rerank for superior document retrieval.

Read our Docs
read docs

About model

Salesforce LlamaRank reranks documents and passages for retrieval tasks, improving the relevance of search results in RAG pipelines. Its key strength lies in reranking precision. Designed for developers building information retrieval and search systems.

    Related models
    Rerank
    Mxbai Rerank Large V2
    • Input/1M
      $0.10
    • Parameters
      1.5B
    No items found.
    Rerank
    Model specifications
    Model data
    • Model provider
      Salesforce
    • Type
      Rerank
    • Deployment
      On-Demand Dedicated
      Monthly Reserved
    • Parameters
      8B
    • Context length
      8192
    • Input price

      $0.10 / 1M tokens

    • Input modalities
      Text
    • Output modalities
      Structured Data
    • Last updated
      February 5, 2026
    • External link
      Provider docs
    • Category
      Rerank
    Quickstart docs
    Deploy model