Do less with serverless: Elastic Cloud Serverless — Now GA
Today, we are pleased to announce the general availability (GA) of Elastic Cloud Serverless on AWS. Elastic Cloud Serverless is the fastest way to start and scale security, observability, and search hassle-free. It’s powered by a re-architectured Elasticsearch that is built on an industry-first Search AI Lake optimized for real-time applications. It combines vast storage with low-latency querying and all of the strengths of Elasticsearch’s AI and search capabilities.
The Elasticsearch everyone loves, reimagined for the cloud
For over a decade, Elasticsearch has redefined search for complex, unstructured data — becoming a key pillar in the AI stack and the go-to solution to make data rapidly searchable at scale. Developers, SREs, and security analysts rely on Elasticsearch for its speed, scalability, and ability to analyze messy, evolving data sets. It runs a range of applications from log analytics to SIEM to AI-driven search. But as data volumes grow and workloads become more complex from retrieval augmented generation (RAG) to threat detection, applications demand even lower latency on ever-growing data sets.
Elasticsearch's new Search AI Lake architecture tackles this head-on with a reimagined stateless architecture. By decoupling compute from storage and indexing from search, the architecture scales seamlessly. What's crucial is that it uses cost-effective cloud-native object storage while retaining Elasticsearch’s fast, low-latency querying and AI relevance capabilities. Enhanced caching and parallelized query processing allow massive data handling with minimal lag, making real-time applications practical and performant. It delivers the storage capacity of a data lake with the responsiveness of Elasticsearch without operational overhead. No need to manage clusters or tune infrastructure — Elastic Cloud Serverless effortlessly handles scaling, storage, and speed automatically. With this architecture, Elasticsearch combines scalability, speed, and simplicity for next-generation, search-powered applications without scale or performance trade-offs.
What has stood out to our team with Elasticsearch Serverless is its ease of use. It’s simple to use as a fully managed service, and it takes virtually no time to set up a new project. We’ve also been impressed with how well Elastic delivers on its autoscaling capabilities.
Marcel Matus, Development Manager, SAP Concur
Many architectural features and innovations were developed to enable low-latency search, efficient data retention, and automatic scalability. For a deeper technical exploration, visit Elastic Search Labs.
Terabytes an hour gives results power
Elastic Cloud Serverless is engineered to tackle high-volume and high-performance workloads. Today, serverless scales to rapidly ingest and efficiently retain petabytes of data with fast indexing, search, and aggregation. Over the past six months since the public preview, thousands of active serverless projects have been provisioned and scaled with customers. Elastic Cloud Serverless recent performance benchmarks demonstrate rapid ingest, high scalability, and fast querying.
Setup is extremely easy. We provisioned a new project without needing technical expertise. Ingesting data and querying the cluster showed nearly zero latency.
Madison Bahmer, Senior Principal Enterprise Architect, Two Six Technologies
Rapidly and predictably ingest hundreds of terabytes a day: As a baseline given ~450K docs/s rate with 3,000 clients, a serverless project can ingest 7.5 terabytes of data per hour to a data stream or over 180 terabytes daily. Ingest rates can be accelerated and optimized further through additional settings. Unlike other platforms, where ingest rates tend to slow down as data volumes grow, Elastic Cloud Serverless provides consistent scaling in both data volume and ingestion speed — even as data sets continue to expand.
The flexibility to be fast, high concurrency querying at scale: Serverless delivers stable and fast query response time. Executing over 3,000 concurrent complex aggregations and queries on 5 terabytes of data delivered consistently low-milliseconds response times.
Actual volume | Duration | Average search rate (req/s) | Max search rate (req/s) | Response time (P50) | Response time (P99) | Load handling search pods | Pod memory |
5.84 TB | 120 minutes | 891 | 3,158 | 36 ms | 316 ms | 24 | 1.2 TB |
Hassle-free operations: The simplest way to start and grow
Elastic Cloud Serverless is designed from the ground up to be the easiest way to start and scale with a simplified user experience.
No nodes, no shards, no stress: No need to manage backend infrastructure, do capacity planning, upgrade, or scale data.
Fast configuration: Start a new fully configured serverless project in a snap.
Guided onboarding: Get a step-by-step process that guides you with in-product resources and tools to get results faster and skip the learning curve.
- Project-based: Explore a new product experience to easily create projects optimized to the unique needs of each use case.
Growing global coverage with AWS regions and upcoming Azure and Google Cloud instances
We are pleased to announce broader geographical availability expanding support for multiple AWS regions from AWS US-East-1 (N. Virginia) to include AWS EU-West-1 (Ireland), AWS AP-Southeast-1 (Singapore), and AWS US-West-2 (Oregon). These regions allow you to run workloads closer to end users, reducing latency and improving overall performance — particularly for search and observability applications. We will continually expand regional support, delivering the flexibility to deploy workloads that meet regional data residency requirements, improve response times, and ensure compliance for data localization.
We are also excited to announce upcoming support for Azure instances. This opens Elastic Cloud Serverless to Microsoft's growing cloud ecosystem for seamless integration with Azure services like Blob Storage, Event Hubs, and Azure Active Directory among many others to streamline workflows. Users can benefit from built-in, enterprise-grade security features to encrypt, secure, and stay compliant while using Azure's global infrastructure. Support for Google Cloud instances will also be available early 2025. Elastic Cloud Serverless multi-cloud strategy will continue to expand flexibility in choosing the best cloud provider based on your requirements and existing cloud deployments.
We also believe in transparency with Elastic engineering by sharing an ambitious roadmap for Elastic Cloud Serverless development. We’ve created a new roadmap page that helps you keep track and see plans for both short- and long-term development.
Streamlined solutions that start fast and search faster
Elastic Cloud Serverless offers both streamlined solutions and pricing. The new solution-specific pricing aligns costs with actual usage tailored to the different needs of security, observability, and search — offering greater flexibility and predictability. This means pricing for log analytics or security events is based on the volume of data ingested and retained, whereas search applications depend on the amount of compute power and storage that is used. By focusing on resource-based metrics like data ingestion, storage, and compute units, Elastic makes it easier for customers to manage budgets and scale as needed — enabling more control to manage workloads across different applications.
We’re also happy to introduce new volume pricing for security and observability data, using a tiered pricing model. This approach simplifies scaling by reducing costs per unit as data usage increases. Pricing decreases with higher data volumes and is divided into tiers based on data ingested and retained. For instance, the first 10 terabytes (TB) of data retention is priced higher per terabyte than the next 10 TB with lower pricing for volumes exceeding 20 TB.
It's also easy to get started with optimized serverless experiences for search, observability, and security.
Elasticsearch Serverless
Elasticsearch Serverless lets developers rapidly build AI-powered search applications with the latest features, save time managing infrastructure, and scale up or down to meet their needs. With optimized instances you can quickly build generative AI (GenAI) applications using both lexical and semantic search that are guided by inline documentation and code samples. Cluster management, scaling, and configurations are all automated and transparent. Users can accelerate development of GenAI applications with access to Elasticsearch’s latest AI capabilities, like vector search and Better Binary Quantization (BBQ), and streamline inference using various built-in or custom models. Read more to dive deep into Elasticsearch Serverless.
Elastic Observability Serverless
Elastic Observability Serverless enables a hassle-free experience without the overhead of managing the Elastic Stack or manually scaling capacity. Streamlined workflows, guided onboarding, and out-of-the-box dashboards and analysis minimize time to insight with crucial context. With over 350+ integrations and an OpenTelemetry-first approach, getting your observability data into Elastic is simpler than ever before. Store both short- and long-term data efficiently without the need for rehydration or data moving across data tiers. This allows quicker than ever analytics with fast queries, RAG-based AI analysis, and machine learning jobs that deliver insights in minutes even on petabytes of data. Analyze all your business and operational data to detect issues proactively, accelerate problem resolution, and deliver on business outcomes. Read more to dive deep into Elastic Observability Serverless.
Elastic Security Serverless
Elastic Security Serverless provides security analysts with a new cloud deployment option for their security analytics and SIEM use cases. This new and fully managed cloud offering delivers a curated security solution that can be put to work quickly. Using Elastic Security Serverless eliminates the overhead of managing cloud and SIEM infrastructure and allows security teams to focus on protecting, investigating, and responding to threats within their organizations. The Search AI Lake architecture offers efficient and fast storage for both short- and long-term data without rehydration or data moving across data tiers. Read more to dive deep into Elastic Security Serverless.
Explore all the power of search and AI, hassle-free
The future of search, security, and observability is here without compromise on speed, scale, or spend. Elastic invites security analysts, SREs, and developers to experience serverless. Learn more about the possibilities of serverless, or start your free trial now.
The release and timing of any features or functionality described in this post remain at Elastic's sole discretion. Any features or functionality not currently available may not be delivered on time or at all.
In this blog post, we may have used or referred to third party generative AI tools, which are owned and operated by their respective owners. Elastic does not have any control over the third party tools and we have no responsibility or liability for their content, operation or use, nor for any loss or damage that may arise from your use of such tools. Please exercise caution when using AI tools with personal, sensitive or confidential information. Any data you submit may be used for AI training or other purposes. There is no guarantee that information you provide will be kept secure or confidential. You should familiarize yourself with the privacy practices and terms of use of any generative AI tools prior to use.
Elastic, Elasticsearch, ESRE, Elasticsearch Relevance Engine and associated marks are trademarks, logos or registered trademarks of Elasticsearch N.V. in the United States and other countries. All other company and product names are trademarks, logos or registered trademarks of their respective owners.