Pricing - Simple, Transparent, Usage Based.

Per-token based pricing for our variety of models via API.

Get started for free.

No credit card required, get started with credits for free. Join Discord or Slack to get help.

Run in Production

Use our API directly in prod to improve your RAG pipeline and get better results.

  • Simple to use API

    Improve your RAG performance, by utilizing SOTA (state-of-the-art) models
  • Fast to integrate

    Use integrations, sdks or simply use our API directly
  • Plug & Play

    Integrate with your existing RAG pipeline, vector database or LLM
  • Multi-purpose

    Use our API for a variety of tasks and domains, including: embeddings, classification, and reranking

Embeddings API

Each model comes with its unique benefits and use-cases. Click on a model for more information.

Enterprise

Dedicated support, instances, custom models, and more. Contact us.

  • Empower Your Solutions with Custom Models

    Elevate your business with models tailored specifically to your data. Choose to train on our cutting-edge infrastructure or on your own premises for unparalleled flexibility.
  • Elevate Performance with Dedicated Instances

    Experience seamless hosting of your models on our high-performance engine. Opt for hosting on our infrastructure, your cloud, or VPC. Our expert team is ready to assist in your setup.
  • Streamline Your Data with Our Expertise

    Let us assist in refining your data. Our team specializes in data collection and cleaning, setting the foundation for a robust and efficient model.
  • Integrate Seamlessly with Custom Solutions

    Enhance your tech stack with bespoke integrations, crafted to mesh flawlessly with your existing systems.