Elastic Managed LLMs
Elastic Cloud Serverless projects are autoscaled environments, fully managed by Elastic and available on Elastic Cloud. Availability This functionality is generally available and ready for production usage. Serverless interfaces and procedures might differ from classic Elastic Stack deployments. The Elastic Stack includes Elastic's core products such as Elasticsearch, Kibana, Logstash, and Beats. Availability This functionality is generally available and ready for production usage. 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.
Serverless
Generally available
Stack
9.0+
Generally available since 9.0
Elastic provides built-in LLMs through managed AI connectors.
These connectors are accessed and managed through the Elastic Inference Service (EIS), which is the single entry point for using Elastic Managed LLMs.
Elastic-Managed-LLM is also the connector ID of Elastic's built-in managed connector in earlier versions. In 9.3, the default model behind this connector was replaced. Existing configurations and saved conversations are migrated automatically to the current default model on more recent versions, so no action is required.
- Requires the
manage_inferencecluster privilege (the built-ininference_adminrole grants this privilege) - Elastic Cloud Enterprise is a self-managed orchestration platform for deploying and managing the Elastic Stack at scale. Availability Generally available This functionality is generally available and ready for production usage. 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. Elastic Cloud on Kubernetes extends Kubernetes orchestration capabilities to allow you to deploy and manage components of the Elastic Stack. Availability Generally available This functionality is generally available and ready for production usage. 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. Self-managed deployments are Elastic Stack deployments managed without the assistance of an orchestrator. Availability Generally available since 9.3 This functionality is generally available and ready for production usage. 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. For on-premises installations (Elastic Cloud Enterprise, Elastic Cloud on Kubernetes, or self managed clusters), Elastic Managed LLMs are only available through EIS with Cloud Connect. Your Elastic Stack version must be 9.3 or later.
Elastic Managed LLMs are available exclusively through the Elastic Inference Service. You can find the list of supported models on the EIS documentation page.
The Elastic Managed LLMs use third party service providers for inference. Refer to the Elastic Inference Service page for details.
Customer projects or deployments hosted in any cloud service provider or region have access to Elastic Managed LLMs. All data is encrypted in transit. The LLMs are configured for zero data retention: none of the prompts or outputs are stored by the service provider.
Only request metadata is logged in AWS CloudWatch. No information related to prompts is retained. Logged metadata includes the timestamp, model used, region, and request status.
Read more at our AI Data FAQs to learn about our data practices for AI related features.
Elastic Managed LLMs incur a cost per million tokens for input and output tokens. Refer to the Elastic pricing page that correspond to your Elastic setup for details.