Gradient Deployments enable a hassle-free, automatic “push to deploy” option for any trained model. These allow ML practitioners to quickly validate “end-to-end” services from R&D to production.


Deploy any model as a high-performance, low-latency micro-service with a RESTful API. Easily monitor, scale, and version deployments. Deployments take a trained model and expose them as a persistent service at a known URI.

Current Capabilities

  • Out-of-the-box integration with TensorFlow models, but can be easily extended to serve other types of models and data.(ONNX coming soon)

  • A variety of GPU & CPU SKUs to deploy to

  • Per Second Billing

  • Multi instance deployments with load balancing

  • Dedicated endpoint URI per deployment

  • Accessible via the CLI, Web UI or API