Skip to content

Baseten

ML model deployment and GPU inference infrastructure

ML model deployment and GPU inference infrastructure. 2 endpoints, free or up to $0.005 per use, sold by Orthogonal.

What your agent can do

  • Send a conversation to a model and get a completion backPOST /baseten/v1/chat/completions$0.005per use
    Price
    $0.005 per use
    Request
    POST https://np.orthogonal.com/baseten/v1/chat/completions
  • Returns the current list of available models with metadata including pricing…GET /baseten/v1/modelsFree
    Description
    Returns the current list of available models with metadata including pricing, context window sizes, and supported features
    Price
    Free
    Request
    GET https://np.orthogonal.com/baseten/v1/models