Type to search.

stack es inference cli namespace

Serverless Preview

Elastic Cloud Serverless projects are autoscaled environments, fully managed by Elastic and available on Elastic Cloud.

Availability

  • Preview

    This functionality is in technical preview and is ready for evaluation. Use with caution in production; it is not recommended for mission-critical workloads. Elastic will work to fix any issues, but features in technical preview are not subject to the support SLA of official GA features. Specific Support terms apply.

Serverless interfaces and procedures might differ from classic Elastic Stack deployments.

Stack Preview

The Elastic Stack includes Elastic's core products such as Elasticsearch, Kibana, Logstash, and Beats.

Availability

  • Preview

    This functionality is in technical preview and is ready for evaluation. Use with caution in production; it is not recommended for mission-critical workloads. Elastic will work to fix any issues, but features in technical preview are not subject to the support SLA of official GA features. Specific Support terms apply.

Unless stated otherwise on the page, this functionality is available when your Elastic Stack is deployed on Elastic Cloud Hosted, Elastic Cloud Enterprise, Elastic Cloud on Kubernetes, and self-managed environments.

This documentation corresponds to the latest patch available for each minor version. If you're not using the latest patch, check the release notes for changes.

Shell 
elastic stack es inference --help

Elasticsearch inference API commands

chat-completion-unified

Perform streaming chat completion inference on the service.

 completion

Perform completion inference on the service.

 delete

Delete an inference endpoint.

 delete-region-policy

Delete the inference region policy.

 embedding

Perform dense embedding inference on the service.

 get

Get an inference endpoint.

 get-region-policy

Get the inference region policy.

 inference

Perform inference on the service.

 non-streaming-chat-completion

Perform non-streaming chat completion inference on the service.

 put

Create an inference endpoint.

 put-ai21

Create a AI21 inference endpoint.

 put-alibabacloud

Create an AlibabaCloud AI Search inference endpoint.

 put-amazonbedrock

Create an Amazon Bedrock inference endpoint.

 put-amazonsagemaker

Create an Amazon SageMaker inference endpoint.

 put-anthropic

Create an Anthropic inference endpoint.

 put-azureaistudio

Create an Azure AI studio inference endpoint.

 put-azureopenai

Create an Azure OpenAI inference endpoint.

 put-cohere

Create a Cohere inference endpoint.

 put-contextualai

Create an Contextual AI inference endpoint.

 put-custom

Create a custom inference endpoint.

 put-deepseek

Create a DeepSeek inference endpoint.

 put-elasticsearch

Create an Elasticsearch inference endpoint.

 put-elser

Create an ELSER inference endpoint.

 put-fireworksai

Create a Fireworks AI inference endpoint.

 put-googleaistudio

Create an Google AI Studio inference endpoint.

 put-googlevertexai

Create a Google Vertex AI inference endpoint.

 put-groq

Create a Groq inference endpoint.

 put-hugging-face

Create a Hugging Face inference endpoint.

 put-jinaai

Create an JinaAI inference endpoint.

 put-llama

Create a Llama inference endpoint.

 put-mistral

Create a Mistral inference endpoint.

 put-nvidia

Create an Nvidia inference endpoint.

 put-openai

Create an OpenAI inference endpoint.

 put-openshift-ai

Create an OpenShift AI inference endpoint.

 put-region-policy

Create or update the inference region policy.

 put-voyageai

Create a VoyageAI inference endpoint.

 put-watsonx

Create a Watsonx inference endpoint.

 rerank

Perform reranking inference on the service.

 sparse-embedding

Perform sparse embedding inference on the service.

 stream-completion

Perform streaming completion inference on the service.

 text-embedding

Perform text embedding inference on the service.

 update

Update an inference endpoint.