API quick reference

Elastic Stack Serverless

All the trained models endpoints have the following base:

/_ml/trained_models/

• Create trained model aliases
• Create trained model definition part
• Create trained models
• Delete trained models
• Get trained models
• Get trained models statistics
• Infer trained model
• Start trained model deployment
• Stop trained model deployment
• Update trained model aliases

You can also integrate NLP models from different providers such as Cohere, HuggingFace, or OpenAI and use them as a service through the inference API.

The inference APIs have the following base:

/_inference/

• Create inference endpoint
• Delete inference endpoint
• Get inference endpoint
• Perform inference