The easiest way to get an API endpoint for any AI model on your own cloud

With Mystic AI you can instantly deploy ML on your own cloud in 3 simple steps

• Authenticate your cloud

  Get started by authenticating your cloud on Mystic with just a few clicks.

  

• Upload your pipelines

  Define the inputs to the endpoint, any pre-processing code, the inference pass, post-processing code and outputs to be returned back from the endpoint.

  View our docs

  ...
  
  @pipe
  def foo(bar: str) -> str:
      return f"Input string: {bar}"
  
  with Pipeline() as builder:
      bar = Variable(str)
      output_1 = foo(bar)
  
      builder.output(output_1)
  
  my_pipeline = builder.get_pipeline()
  my_pipeline.run("test")
  
  ...

• Start sending requests

  Once your pipeline has been deployed, start sending inference requests using our API.

  curl -X POST 'https://www.mystic.ai/v4/runs' 
    --header 'Authorization: Bearer YOUR_TOKEN' 
    --header 'Content-Type: application/json' 
    --data '{
      "pipeline": "YOUR_PIPELINE",
      "input_data": {}
    '