Training Example: ClickHouse – Review the Data, Give Your Score & Compare to the Real AI Evaluation

[H1] The leadingdatabase for AI
Powering agentic systems with millisecond queries at petabyte scale.Start free cloud trialContact sales
[IMG: logo]
Langfuse is now part of ClickHouse. Discover the leading open-source platform for LLM observability, evaluations, and prompt management. Ideal for building, monitoring, and optimizing AI applications at scale.ClickHouse is trusted byPrevious slideNext slideUse cases
[H2] Built for every modern data challenge
[IMG: Real-time analytics]
[IMG: Icon for Real-time analytics]
[H3] Real-time analytics
->Deliver instant insights and dashboards at scale. Analyze billions of rows in real time with millisecond results.
[IMG: Observability]
[IMG: Icon for Observability]
[H3] Observability
->Store and query logs, metrics and traces at scale using ClickStack, the open source observability stack powered by ClickHouse.
[IMG: Data warehousing]
[IMG: Icon for Data warehousing]
[H3] Data warehousing
->Analyze and explore data instantly for insights and apps. Scale faster by offloading heavy workloads.
[IMG: ML & GenAI]
[IMG: Icon for ML & GenAI]
[H3] ML & GenAI
->Power machine learning and GenAI with blazing-fast vector search, instant aggregations, and scalable training.
[H2] Build real-time data products that scale
Sony, Lyft, Cisco, GitLab and many more choose ClickHouse Cloud for its scale, efficiency, and ease of use.Filter byReal-time analyticsObservabilityBusiness intelligenceMedia & entertainmentML & GenAIFinancial servicesMarketing & salesE-commerce & retailFraud & cybersecurityGaming
[IMG: Video Thumbnail]
“ClickHouse played an instrumental role in helping us develop and ship Claude 4.”Anthropic
[IMG: Video Thumbnail]
“ClickHouse checked every box. We have availability, we have speed, we have durability. We have everything we could want.”Tesla
[IMG: Video Thumbnail]
“We needed something to slice and dice real-time data, like rides and driver hours across cities and regions where Lyft runs. Using ClickHouse resulted into a lot of performance benefits for us with huge cost savings for the org.”LyftView all use cases
[H2] Why ClickHouse?
ClickHouse is the fastest and most resource efficient real-time data warehouse and open-source database.
[H3] Blazing fast
Ultimate query performance that your mission-critical and time-sensitive applications can depend on.
[H3] Developer friendly
Built to ensure that even the most sophisticated data analysis can be done intuitively, using simple SQL.
[H3] Cost effective
Best-in-class compression ratios that reduce storage and accelerate performance.
[H3] OpenSource
More ->
[H3] Secure,compliant
More ->
[H3] Resourceoptimized
More ->
[H3] Provenat scale
More ->
[H3] 100+integrations
More ->Get started in a few minutes with a free cloud trial ->
[H2] Seamlessly integrate with your stack
Choose from our growing ecosystem of integrations for data ingestion, visualization, language clients, and more.
[IMG: Stack integration graph]
[IMG: Fast Icon]
[H2] Why is ClickHouse so fast?
Column-oriented databases are better suited to OLAP scenarios. They are at least 100x faster in processing most queries. ClickHouse uses all available system resources to their full potential to process each analytical query as fast as possible.Row-oriented databasesIn row-oriented databases, data is stored in rows, with all the values related to a row physically stored next to each other.Column-oriented databasesIn column-oriented databases, like ClickHouse, data is stored in columns, with values from the same columns stored together.Read more in the docs
[H2] Deploy your way
Unlike traditional closed-source databases, ClickHouse runs in every environment, whether it’s on your machine or in the cloud.
[H3] ClickHouse Cloud
The best way to use ClickHouse. Available on AWS, GCP, Azure and, on their respective marketplaces.Get started
[H3] ClickHouse
Spin up a database server with open-source ClickHouse. Always free.Download ClickHouse
[H3] ClickHouse Local
Run fast queries on local files (CSV, TSV, Parquet, and many more) without a server.Download ClickHouse Local
[H2] Join the 100k+ developers using ClickHouse today
[IMG: X]
X
[IMG: Slack]
Slack
[IMG: Telegram]
Telegram
[IMG: Meetup]
Meetup
[IMG: LinkedIn]
LinkedIn2.9k+Contributors28.9k+PRs796+Releases47.6k+Stars
[IMG: FAQ Icon]
[H2] FAQs
Wherever you need us, we’re there. We love to engage in thoughtful conversation with the ClickHouse community and are always on-hand to answer your questions. Ask us anything 01Why should I use ClickHouse vs. X database?ClickHouse is faster than most traditional data warehouses and databases and is most often used when real-time queries on large datasets are necessary at an affordable cost. However, developers also often use ClickHouse on top of their CDWH or OLTP databases to act as a “speed layer” within their existing infrastructure.02What is OLAP?OLAP stands for “online analytical processing” which contrasts from OLTP, or “online transaction processing.” As the name suggests, OLAP databases perform significantly better compared to OLTP databases for analytical workloads common with large datasets.03How does ClickHouse handle large amounts of data?In order to easily process large amounts of data, ClickHouse uses highly optimized compression techniques and vectorized query execution to maximize CPU efficiency.04How does ClickHouse support data visualization and analysis?ClickHouse supports connectors to many clients and drivers, including common BI and data analysis tools. Please see this page for a complete list of supported integrations.05How much does ClickHouse cost?Self-managed ClickHouse is dependent on the cost of your compute and data storage resources, as well as headcount necessary to manage the ClickHouse deployment. For the most affordable way to run ClickHouse, use ClickHouse Cloud, which starts at $50/month.
[H2] Start using ClickHouse in seconds
Install ClickHouse for MacOS, Linux, and FreeBSD.$curl https://clickhouse.com/ | shOr install for Windows, Docker or see other install options. Or try without installing in our playground.Watch this getting started video to learn more about ClickHouse.

[H1] User stories
Discover how companies are using ClickHouse to speed up their workloads and lower costs.LatestUse caseMigrationVerticalProviderClear filtersReal-time analyticsTrouble will find you: How Cloudflare uses ClickHouse to scale analytics at quadrillion-row scale“At Cloudflare, we’re always scaling. There’s always more trouble tomorrow. But we’ve designed our system around ClickHouse to be able to deal with that.”
Jamie Herre, Senior Director of Engineering
Data warehousingDriving Precision: How Changan Ford Saved 40% with ClickHouseMigrating from a self-managed ClickHouse cluster to ClickHouse Enterprise Edition on Alibaba Cloud cut annual compute and storage costs by more than 40%. With compute-storage separation and an elastic, pay-as-you-go billing model, resources are provisioned only when they’re actually needed.ObservabilityScaling observability at Character.AI: thousands of GPUs, 10x logs, and 50% lower cost with ClickStack"Previously, querying the last 10 minutes would take 1–2 minutes. With ClickStack, it was just a case of how fast I could blink. The performance is real. When you're digging into logs during an incident, every second matters."
Mustafa Yildirim, SRE at Character.AIObservabilityHow Tesla built a quadrillion-row-scale observability platform on ClickHouse“Data in ClickHouse is better than data anywhere else. No other system lets you slice and dice your data, ask interesting questions, and get answers in an acceptable amount of time. There’s nothing out there that competes with ClickHouse.”
Alon Tal, Senior Staff Software Engineer, TeslaObservabilityHow Anthropic is using ClickHouse to scale observability for the AI era"ClickHouse played an instrumental role in helping us develop and ship Claude 4. With ClickHouse, the database is green, queries are lightning-fast, and money is not on fire. ClickHouse has already delivered significant value in helping us create state-of-the-art language models."ObservabilityWhy OpenAI chose ClickHouse for petabyte-scale observability“A lot of our peer companies are using ClickHouse for this exact use case (observability). It’s battle-tested and just the right tool for the job.”
Akshay Nanavati, Engineering ManagerReal-time analyticsBuilding a Scalable Analytics Platform: Why Microsoft Clarity Chose ClickHouse"Compared to our POC system, ClickHouse outperformed Elastic Search and Spark in every aspect. Heat map generation became an instantaneous task to do, and it was even orders of magnitude cheaper to run. This is the reason why many products have migrated from Elastic Search to ClickHouse, experiencing significant enhancements in their services as a result." -Omar Bazaraa, Software EngineerReal-time analyticsHow Memorial Sloan Kettering Cancer Center is using ClickHouse to accelerate cancer research“ClickHouse proved to be 10 times faster than our legacy MySQL system.“
Aaron Lisman, Lead Software Engineer
Real-time analyticsWhen you're in the database space, it's hard not to hear about ClickHouse!“We’ve had a positive experience with ClickHouse. It allowed us to scale LangSmith to production workloads and provide a service where users can log all of their data. We couldn’t have accomplished this without ClickHouse.”ObservabilityHow the D. E. Shaw group powers high-cardinality observability at scale with ClickHouse“We found ClickHouse to be a superior tool for enabling a top-level view and detailed low-level analysis of our high-cardinality time-series metrics data. I think teams seeking high-performance observability platforms should certainly consider it as a candidate solution.”
Mike Vasiliou, Site Reliability Engineer
Data warehousingPowering self-driving vehicle analytics at Avride with ClickHouse Cloud Avride uses ClickHouse Cloud as the data backbone for its autonomous vehicle and delivery robot fleet, powering indexing, metrics, and analytics company-wide.Real-time analyticsHow Critical Manufacturing uses ClickHouse to bring real-time intelligence to the factory floorCritical Manufacturing uses ClickHouse to power real-time analytics and operational intelligence, turning billions of shop-floor events into sub-second insights. ObservabilityHow Nava helped ELO cut infrastructure costs by 87% by migrating from Elasticsearch to ClickHouse"ClickHouse is on a different level. The first time you have contact with it, its performance is absurd."
Lucas Souza, Data Engineer and Architect at NavaObservabilityTrio“In terms of speed, ClickHouse is truly undisputed. It’s a generational leap compared to what we had, even with minimal tuning.” Filipe Coelho, Data SpecialistObservabilityGoodbye limitations, hello data: How Qonto is rethinking observability with ClickHouse CloudAs an observability guy, cardinality was a scary word for us. Now it’s something I actively root for.
Javier Ortiz, Tech Lead for SRE Observability - QontoReal-time analyticsGala Supercharges Analytics Performance with ClickHouse on AWSGala migrated to ClickHouse Cloud on AWS, cutting costs 30% and tripling analytics data capacity, giving game developers and marketers the real-time insights needed to optimize player experience and drive growth.Real-time analyticsMintlify boosts NPS 30% and saves 60% with real-time analytics on ClickHouse CloudAfter replacing PostHog with ClickHouse Cloud, Mintlify reduced dashboard load times to under one second, significantly improving the customer experience and boosting NPS by an estimated 30%, while also achieving a zero-maintenance solution at 60% lower cost that scales far beyond its current needs.Real-time analyticsHow Eisan made POS analytics faster, cheaper, and more reliable with ClickHouse Cloud“ClickHouse’s speed is absolutely incredible. More than that, it’s reliable. Unlike our previous QlikView-based system, we’ve never had a case where ClickHouse failed to return a result.” Mamoru Ubukata, Representative DirectorReal-time analytics, ObservabilityHow Respan is scaling LLM observability with ClickHouse Cloud"Since moving to ClickHouse, we can now easily handle the scale that we couldn’t before." Raymond Huang, Co-Founder and CTOReal-time analyticsRill and ClickHouse: real-time operational BI for a metered world“A lot of BI tools treat heavy queries as something to be avoided. Because we’ve built around a real-time database like ClickHouse, we’re able to do things other dashboards wouldn’t even attempt to do.”
Mike Driscoll, Co-Founder and CEO
Real-time analyticsHow Padlet uses ClickHouse Cloud to power real-time classroom analytics“In just one month, we ingested nearly 8 billion events into ClickHouse. We’re now handling 14 requests per second, well beyond our original goal, with a median latency of just 45 milliseconds. For teachers, engagement data isn’t an afterthought anymore. When someone clicks, they see the results immediately.” - Zoheb Jamal, VP of GrowthMachine learning and GenAIIntelligent security at ClickHouse speed: How Cogent Security built an AI-native vulnerability management platform"The key thing that ClickHouse unlocks for AI is speed. Everything we do needs to be done at machine speed to counter AI-enabled attackers.”
Karan Gugle, Founding EngineerReal-time analytics, Managed PostgresSocialpruf“It gives a real ‘wow’ effect for our customers. We have a great UX, and combining that with the speed of ClickHouse makes for a great user experience.”
“We’re very satisfied with the combination of Postgres and ClickHouse. It just works and fulfills our needs. As we grow, it’ll play a bigger role.”
Semyon Khlavich, Founder and CTO
Real-time analyticsReploReplo uses ClickHouse to power real-time, in-product analytics for Shopify merchants running live pages, offers, and A/B tests. The team iterated through multiple data models, learning how precomputation, deduplication, and recomputation boundaries affect real-time analytics at scale. Today, ClickHouse supports ingestion of 3,000-5,000 events per second and analysis of 100+ billion events while keeping dashboards fast and responsive.Real-time analyticsA million events per second: How Lago scales usage-based billing with ClickHouse Cloud“We tried so many databases. The only one that worked really well and that was really easy to understand was ClickHouse.”
“We’re the only billing solution that can provide one million events per second ingestion. Without ClickHouse, this wouldn't be possible.”
Jérémy Denquin, Engineering LeadReal-time analyticsHow InMobi achieved 20x faster queries and 80% cost savings with ClickHouse“We adopted ClickHouse for speed. It ended up delivering not just speed, but helping us build a platform that’s fast, reliable, and predictable on a cost basis.” - Anand Tirthgirikar, Staff EngineerReal-time analyticsHow Luzmo uses ClickHouse Cloud to power fast end-user analytics“ClickHouse Cloud has been quite infectious inside our company. It’s extremely fast, extremely versatile, and extremely cost-efficient.”
Haroen Vermylen, Co-Founder and CTOObservabilityHow LY Corporation uses ClickHouse to observe one of the largest Kafka deployments on earth“ClickHouse plays a really important role in our automated monitoring efforts. We’re handling a massive amount of data—about seven million rows per second—but with just 24 servers, we’ve achieved outstanding cost performance.” - Haruki Okada, Senior Software EngineerReal-time analyticsHow Silverflow simplified its data platform and cut end-to-end latency by 95% with ClickHouse Cloud“With ClickHouse, events are faster to query, and they’re also available to be queried much faster, which has enabled us to do more real-time dashboarding and faster alerting.”
Roberta Gismondi, Software EngineerObservabilityHow Langfuse is scaling LLM observability for the agentic era with ClickHouse Cloud “We’re building observability for engineering teams working on the most complex and advanced agentic systems. ClickHouse has served us really, really well.”
Max Deichmann, Co-Founder and CTOReal-time analytics, Machine learning and GenAIHow DoControl delivers real-time, AI-driven SaaS security insights with ClickHouse Cloud and MCP“We were super excited to start working with ClickHouse. It has been a game-changer in how we serve the world’s largest companies, in a way that no competitive solution can match.”
Amit Fidler, Director of Engineering
“As DoControl grew, we needed a data infrastructure that could support the scale. ClickHouse met the mark.”
Bar Ifrah, Technical LeadObservabilityLovable <3 ClickHouse: AI-powered observability and analytics at the world’s fastest-growing software company“At Lovable, we're making it possible for anyone to build software. ClickHouse makes it possible for anyone—human or AI—to understand and analyze that software at scale.”
Tomas Nordström, Member of Technical StaffReal-time analyticsHow Buildkite transformed test analytics and cut costs with ClickHouse Cloud“Shifting workloads to ClickHouse Cloud has simplified our backend systems and reduced costs, unlocked more possibilities for analytics, and enabled the team to rapidly deliver new functionality.”
Gordon Chan, Staff Software EngineerReal-time analyticsHow ClickHouse Cloud enabled LaunchDarkly to build and ship features faster“With ClickHouse, we can serve fresh data, query raw events directly, lean on materialized views when needed, and build new capabilities in weeks instead of months or quarters.”
Joe Karayusuf, Software Engineer at LaunchDarklyReal-time analytics“Just OLAP it”: How Ramp rebuilt its analytics platform on ClickHouse Cloud“ClickHouse has played a critical role in powering our growth the past two years. We love ClickHouse Cloud. It’s been a game-changer for us.”
Ryan Delgado, Director of Engineering
Real-time analyticsHow Picnic uses ClickHouse for real-time analytics across 20+ fulfillment centers and 1 million unique stores“ClickHouse is very easy to operate, very cost-effective, and scaling is really simple with ClickHouse Cloud. We’re very happy with it.”
Max Sumrall, Software EngineerReal-time analytics, Data warehousingPolymarket scaled their data stack with Postgres and ClickHouse"I knew that ClickHouse was fast and that we could run these aggregates in milliseconds, whereas it would literally time out with Postgres." - Max "Primo" Mershon, Senior Data Engineer at PolymarketReal-time analyticsHow HighLevel rebuilt its data platform for speed, scale, and simplicity on ClickHouse Cloud“With ClickHouse, we saw a whopping 88% reduction in storage, and P99 queries dropped from 6+ seconds to less than 200 milliseconds.” - Pragnesh Bhavsar, Staff EngineerReal-time analyticsHow Chartmetric is scaling music analytics with ClickHouse“ClickHouse works very well as part of our multi-system data stack. It’s excellent for time-series data, and the VersionedCollapsingMergeTree engine was a game-changer for us, speeding up queries from 20 seconds in Snowflake to 1.5 seconds in ClickHouse.”
Umang Sharaf, Lead Data EngineerReal-time analyticsEMQ and ClickHouse: Real-time, AI-assisted analytics at the industrial edge“EMQ enables real-time data integration. ClickHouse makes it possible to process large-scale data in real time.”
“By using ClickHouse MCP, you can perform highly complex analytics, monitor data, and exercise fine-grained control.”
Cheng Sun, Solution Architect
Real-time analyticsHow GitLab serves sub-second analytics to 50 million users"We've consistently run into scaling and performance bottlenecks that limited our ability to deliver the kind of analytics features our users needed. ClickHouse gave us the breakthrough we needed to deliver the kind of features we’d been holding back."
Dennis Tang, Senior Engineering ManagerReal-time analyticsHow Pump uses ClickHouse Cloud to bring cloud costs into focus“We built Pump View to give users more visibility into their cloud spend. All of this is driven under the hood by ClickHouse.”
“When you insert data, it shouldn’t slow down your queries, and when you’re querying, it shouldn’t slow down your inserts. ClickHouse is optimized to split up data ingestion and data analysis.”
Joel Walker, Founding Software EngineerReal-time analyticsHow Canva achieved 10x faster search and 70% lower costs with ClickHouse“Moving to ClickHouse, we managed to get 70% cheaper costs and improved our search performance by 10x. We’re doing more and storing more with less.”
Zjan Carlo Turla, Software EngineerReal-time analyticsHow FabFunnel powers real-time marketing analytics with ClickHouse Cloud“Our query efficiency has improved significantly since moving to ClickHouse. We can now show our clients real-time analytics.” - Sidhant Gaba, EngineerReal-time analyticsScaling SaaS security: Reco’s migration from Postgres to ClickHouse Cloud“Cost has gone down, speed has gone up, and the scale of our customers has increased exponentially.”
Nir Barak, Principal Data EngineerReal-time analyticsHow Merkle Science fights crypto crime at scale with ClickHouse Cloud“Even if data increases by 4x or 5x in the next year, we

Managed ClickStack
[H1] Observability for OpenTelemetry at scale
Never sample. Retain everything. Unlimited queries.Stop choosing between cost and clarity and losing those events which matter.With full-fidelity, long-term OpenTelemetry data, you gain complete visibility for your users and agents, removing blind spots and enabling faster MTTR and true RCA.Start free trialContact salesNever sample, roll up, or discard high cardinality telemetryIndefinite retention of high-cardinality logs, metrics, trace at sub-cent per GB storage pricingUnlimited fast queries and atleast 10x compression10x-100x more cost effective
[IMG: ClickStack Dashboard]
Trusted for observability by
[IMG: Netflix logo]
[IMG: Cloudflare logo]
[IMG: Sony logo]
[IMG: Comcast logo]
[IMG: Anthropic logo]
[IMG: Character.ai logo]
[IMG: Sierra logo]
[IMG: Ebay logo]
[IMG: Cisco logo]
[IMG: DoorDash logo]
[IMG: GitLab logo]
[IMG: IBM logo]
[IMG: SolarWinds logo]
[IMG: Vimeo logo]
[IMG: Netflix logo]
[IMG: Cloudflare logo]
[IMG: Sony logo]
[IMG: Comcast logo]
[IMG: Anthropic logo]
[IMG: Character.ai logo]
[IMG: Sierra logo]
[IMG: Ebay logo]
[IMG: Cisco logo]
[IMG: DoorDash logo]
[IMG: GitLab logo]
[IMG: IBM logo]
[IMG: SolarWinds logo]
[IMG: Vimeo logo]
[IMG: Quote]
At Sony LIV, we ingest tens of millions of video streaming events into ClickHouse Cloud and run queries to generate complex dashboards for analysis. This allows our operations team to monitor, alert & troubleshoot the QOS and QOE of our customers in real-time. ClickHouse Cloud has helped us to optimize costs and ensure the high availability and resilience of our services.
[IMG: Quote]
ClickHouse played an instrumental role in helping us develop and ship Claude 4. With ClickHouse, the database is green, queries are lightning-fast, and money is not on fire. ClickHouse has already delivered significant value in helping us create state-of-the-art language models.
[IMG: Quote]
Previously, querying the last 10 minutes would take 1-2 minutes. With ClickStack, it was just a case of how fast I could blink. The performance is real. When you’re digging into logs during an incident, every second matters.
[H2] The observability solution powered by ClickHouse Cloud
[IMG: Timer icon]
[H3] Sub-second queries
Even on hundreds of petabytes of high cardinality unsampled OpenTelemetry data.
[IMG: Stack icon]
[H3] Full stack OTel observability
Unify Session Replays with OTel Logs, Traces and Metrics.
[IMG: Coins icon]
[H3] Market leading cost efficiency
30x OpenTelemetry compression with object storage and flexible compute for major cost savings.
[IMG: Savings icon]
[H3] Unlimited retention
Separation of storage and compute, means long-term retention for less than a cent per GB per month.
[H2] Ingest everything.Retain everything.
Handle petabytes of OpenTelemetry data with the full power of open source ClickStack. Delivered as a simple, fully managed service.No samplingNo rollupsNo retention tradeoffsManaged ClickStack scales storage and compute independently to petabytes, exploiting 30x compression and object storage to let you retain high-cardinality data long term at less than a cent per GB while keeping queries fast and costs predictable.ClickStackCompute groups
[IMG: ClickHouse logo]
NodeNodeWritesNodeNodeNodeNodeReadsNodeAlertsData CacheProcess datain parallelProcess datain parallelProcess datain parallelProcess datain parallelObjectstorageInfiniteretention
[H2] Store everything.Scale flexibly.
ClickHouse's full separation of storage and compute enables flexible scaling and long term retention without operational tradeoffs.Low cost object storage by defaultNode level caching for sub second queriesDynamically scalable computeCompute runs independently in front of storage and can be scaled vertically or horizontally based on workload demands.Isolate resources for ingestion, querying, dashboards, or alerting workloads so heavy reads or bursts of traffic never impact critical pipelines.
[H2] Unlock your agentic observability workloads
AI notebooksPower your agents
[H3] Built-in collaborative AI workflows with Notebooks
ClickStack provides a native, AI-assisted notebook experience where SREs and AI work together to investigate systems.
[H3] Intelligent investigation
AI-assisted analysis across logs, metrics, traces
[H3] Hybrid interaction
Natural language + SQL workflows
[H3] Transparent operations
Visible reasoning, auditable queries
[H3] Collaborative orkspaces
Persistent, shareable environmentsLoading video...
[H2] Enterprise-grade observability, made simple
Getting started with Managed ClickStack takes minutes. Specify how much data you plan to ingest, create your service, start sending and enjoy enterprise-grade capabilities out of the box.
[IMG: Shield icon]
[H3] Uncompromising reliability
Replicated across multiple availability zones by default, ClickHouse Cloud provides high availability, seamless upgrades, automated backups, and built-in disaster recovery.
[IMG: Lock icon]
[H3] World-class security
Enterprise-grade security is built in from day one. ClickHouse Cloud offers strong user and network access controls, encryption in transit and at rest, comprehensive activity logging, and SOC 2 Type II compliance.
[IMG: Reliability and security]
[H3] Searches, dashboards, and alerts
ClickStack unifies logs, metrics, traces, and session replays in one platform via the ClickStack UI (HyperDX). Optimized for ClickHouse, it supports fast Lucene-style search and full SQL access for advanced analysis and deeper analysis powered by over 100+ built-in functions.Create dashboards and alerts with minimal setup. Spot anomalies with event deltas and speed up root cause analysis using event patterns.
[H3] ClickHouse Cloud powered storage
Powered by ClickHouse Cloud, ClickStack searches terabytes of OTel data in seconds and ingests billions of high-cardinality events daily with optimized OTel schemas out-of-the-the-box.ClickHouse Cloud’s brings scaling and cost efficiency through full separation of storage and compute. Ingestion and queries can be completely isolated on dedicated resources, thanks to compute-compute separation. This ensures consistent performance at any scale while allowing further cost-efficiency optimizations to be made.
[H3] Data collection
ClickStack natively supports the OpenTelemetry standard, capturing logs, metrics, and traces as wide events - context-rich records that unify observability data in ClickHouse. Designed for OTel data at Petabyte scale.With native JSON support, ClickHouse efficiently handles evolving, semi-structured data. Fields are created automatically on ingest, with compressed columnar storage delivering fast queries and high compression with no upfront schema required.Start free trial
[H2] Introduction to Managed ClickStack
[IMG: YouTube Video: pa_dyNdAHC4]
[IMG: YouTube Video: WBe7ZwTRWuQ]
[IMG: YouTube Video: 3waDYancX_c]
[H2] Intuitive observability workflows
Intuitive observability UI for incident-driven workflowsLucene-style search and SQL, side by sideAutomatic correlation of logs, traces, and metricsService Maps, patterns, clustering, and dashboards built inClickHouse-native optimizations for fast queries at scale
[H2] Only pay for the compute you need, when you need
ClickHouse Cloud lets you match compute to how your observability data is used, with dedicated resources for ingestion, separate pools for common queries on recent data, and on-demand compute for long-tail or historical analysis.With isolated read and write paths and independent scaling, combined with the ability to idle or pause unused compute, you only pay for resources while they are actively in use.
[H2] Why use Managed ClickStack for your observability?
[IMG: Savings icon]
[H3] Reduce your observability costs
Managed ClickStack combines ClickHouse’s open source efficiency with cloud-native storage and compute separation to deliver low-cost observability at any scale.Ingestion and queries scale independently, data is retained indefinitely on object storage, and columnar compression reduces OpenTelemetry data by up to 90 percent, eliminating the need for sampling or short retention windows even at petabyte scale.
[IMG: Sparkles icon]
[H3] Simple deployment and maintenance
Managed ClickStack deploys in a few clicks. Specify your monthly OpenTelemetry ingest and start sending data in standard formats while backups, upgrades, scaling, and maintenance are handled automatically with no infrastructure to manage.Separation of storage and compute enables near-infinite scale while ingest and query compute can be isolated to ensure predictable performance and optimize cost.
[IMG: File icon]
[H3] Real-time observability
ClickHouse Cloud is built for continuous, high-volume ingestion, supporting gigabytes per second while making data searchable in seconds. Materialized views compute common metrics at insert time, to selectively accelerate query time workloads.The ClickStack UI automatically uses these views to keep dashboards fast and interactive, even across hundreds of petabytes of high-cardinality data.
[IMG: Light bulb icon]
[H3] Beyond observability
The engine behind Managed ClickStack, ClickHouse Cloud, is more than an observability store. It is a high-performance SQL analytics database with fully managed ingestion through ClickPipes, including sources like Kafka, and native data lake support for querying data directly in your data lake.Observability becomes part of a broader analytics workflow, letting you join telemetry with business and security data in one system and analyze it through BI tools, notebooks, and dashboards for deeper correlation.
[H3] Subscribe to our observability newsletter
Stay informed on ClickStack feature releases, product roadmap, support, and cloud offerings!Loading form...
[H2] Instrument your applications
Trace every log, API request, DB query, and more with just a few lines of code. Instrument and observe your stack in minutes with ClickStack.
[IMG: NodeJS]
[IMG: Go]
[IMG: Java]
[IMG: Javascript]
[IMG: NextJS]
[IMG: Python]
[IMG: Ruby]
[IMG: Cloudflare]
[IMG: Kubernetes]
[IMG: OpenTelemetry]
[IMG: AWS]
[IMG: Fluentd]
[H2] Try ClickStack in ClickHouse Cloud
Experience the full power of HyperDX + ClickHouse in just minutes.We’ll get you started on a 30 day trial and $300 credits to spend at your own pace.Get started
[IMG: FAQ Icon]
[H2] FAQs
We're here to make observability simple, fast, and open. Explore our FAQs to learn more about Managed ClickStack, and if you don’t see what you need, we’re always happy to chat.Ask us anything ->->01What is Managed ClickStack?Managed ClickStack is the fully managed version of the open source ClickStack observability stack, running on ClickHouse Cloud. It delivers the same high-performance, open source foundation for logs, metrics, traces, and session replays, without the operational burden of running and maintaining the underlying ClickHouse infrastructure.
ClickHouse Cloud handles cluster management, scaling, upgrades, and reliability for you, while adding enterprise-grade capabilities such as separation of storage and compute and low-cost object storage for long-term retention. This lets you retain high-cardinality OpenTelemetry data indefinitely, minimize costs, and focus entirely on observability and insights rather than platform operations.02How does Managed ClickStack compare to Elastic Cloud?At a glance, Managed ClickStack and Elastic Cloud look familiar. Both provide an end-to-end observability stack with data collection, storage, and a UI for search, dashboards, and analysis. OpenTelemetry and Beats serve similar roles, HyperDX and Kibana feel conceptually alike, and both platforms aim to make large-scale observability data accessible.
The key difference lies in the underlying architecture. Elastic Cloud is built on Elasticsearch, a distributed search engine optimized around inverted indices and shard-based storage. This works well for text search, but comes with higher storage overhead, limited compression, and increasing contention between ingest and query workloads as data volumes and cardinality grow. Elastic Cloud’s serverless offerings improve operational simplicity and long-term retention through object storage, but the core search-centric architecture remains.
Managed ClickStack is built on ClickHouse Cloud, a column-oriented analytics engine designed for high-cardinality data and fast aggregation at scale. Columnar storage enables dramatically higher compression, while massively parallel query execution delivers faster aggregations and analytics across large datasets. In ClickHouse Cloud, separation of storage and compute allows low-cost object storage for long-term retention, independent scaling of ingest and query workloads, and predictable performance as data grows.
The result is a platform that feels familiar to users of Elastic, but delivers lower storage costs, faster analytical queries, and greater efficiency for real-time observability and long-term analysis at petabyte scale.
For more details on how ClickStack compares with the ELK Stack see our comparison guide.03What are the core components of ClickStack?The ClickStack consists of three core components:
ClickHouse - The columnar database powering fast, cost-efficient queries and compression.
ClickStack UI (HyperDX) - The unified UI for search, dashboards, alerts, and session replays.
OpenTelemetry - Standardized data collection for logs, metrics, and traces.
Together, they form a single, integrated observability stack optimized for speed, scalability, and simplicity.04Is Managed ClickStack compatible with OpenTelemetry?Yes. Managed ClickStack is built for OpenTelemetry at any scale. Via an OpenTelemetry Collector users can ingest OTel events to ClickHouse - combining logs, metrics, and traces into a unified model.
Although Managed ClickStack is OpenTelemetry-native, it also supports any wide event format. While OpenTelemetry schemas are provided out of the box, users can bring their own - just include a timestamp, and the UI with ClickHouse delivers the same powerful querying, correlation, and visualization capabilities.05Is Managed ClickStack only compatible with OpenTelemetry?No. While Managed ClickStack is optimized for the OpenTelemetry schema, making it the fastest way to get started and scale easily, it’s not limited to it. ClickHouse, the database powering ClickStack, can store and query any event schema.
Only a timestamp field is required to render and visualize events, so you can use your own data formats or custom pipelines. By following a wide events pattern and including a timestamp, your data becomes immediately usable.06Can I store logs, traces, and metrics in Managed ClickStack?Yes. Managed ClickStack is a full observability solution designed to handle logs, traces and metrics in one place. Built on ClickHouse, it efficiently ingests and stores high-cardinality OpenTelemetry data, automatically correlating events at the database layer for de

[H1] Use cases
Unlock faster queries and the ability to handle greater concurrency. No matter how much data you’re working with.Start your free Cloud trialLearn moreReal-time analyticsPower interactive applications and dashboards that analyze and aggregate large amounts of data on the fly. Run complex internal analytics in milliseconds, not minutes or hours.
Relied on by companies all over the world to process tens of billions of new events per day.Learn moreObservabilityMonitor with confidence your logs, events, traces, and other time series data. Detect anomalies, fraud, network or infrastructure issues, and more.
Used at scale to ingest millions of records per second as the trusted SQL-based observability store.Learn moreData warehousingInteractively slice and dice your data for analysis, reporting, and building internal applications. Leveraged to better understand business usage, user behaviors, ad performance, market dynamics, and more. Offload your workloads from traditional warehouses and lakes for speed and efficiency at scale.Learn moreMachine learning and GenAIExecute fast and efficient vector search. Plug-and-play Generative AI models from any provider. Use lightning-fast aggregations to power model training at petabyte scale.
A central data store for your machine learning workloads.
[H2] Comparisons
ClickHouse excels at powering workloads that operate on both real-time and historical data.In contrast, traditional warehouses and transactional databases lack the performance and cost efficiency that makes them viable for analytic workloads at scale.With ClickHouse, you’ll have unrivaled performance and visibility into your data at a fraction of the cost.
[H3] ClickHouse vs Snowflake
[IMG: 2x Faster queries]
[H3] 2x
Faster queries
[IMG: 38% Better compression]
[H3] 38%
Better compression
[IMG: 3-5x Reduction in cost]
[H3] 3-5x
Reduction in cost"Over time, those queries had become painfully slow in Snowflake and Postgres. Some took over a minute. Others timed out entirely...The payoff [of migrating to ClickHouse] came right away. Queries that once failed now ran in six seconds, with no caching required."
[IMG: Logo]
[H3] ClickHouse vs PostgreSQL
[IMG: 1000x Faster queries]
[H3] 1000x
Faster queries
[IMG: -50% Disk space]
[H3] -50%
Disk space
[IMG: 5x Cost savings]
[H3] 5x
Cost savings"It is instant in ClickHouse vs forever in Postgres."
[IMG: Logo]
[H3] ClickHouse vs BigQuery
[IMG: 10x Better performance]
[H3] 10x
Better performance
[IMG: 30x Compression ratios]
[H3] 30x
Compression ratios
[IMG: 10x OpEx reduction]
[H3] 10x
OpEx reduction"We simply don’t want the hassle of trying to figure out in advance how many BQ slots to purchase - what a headache!"
[IMG: Logo]
[H3] ClickHouse vs Redshift
[IMG: 5x Query performance]
[H3] 5x
Query performance
[IMG: 75% Reduction in cost]
[H3] 75%
Reduction in cost
[IMG: 20x Concurrency]
[H3] 20x
Concurrency"Moving over to ClickHouse we were basically able to cut that (Redshift) bill in half."
[IMG: Logo]
[IMG: Quote]
When we moved into the LLM observability and analytics space, we decided to back LangSmith with ClickHouse instead of Postgres. Ankush, CTO of LangChain
[IMG: Quote]
ClickHouse helps us efficiently and reliably analyze logs across trillions of Internet requests to identify malicious traffic and provide customers with rich analytics.
[IMG: Quote]
Now, our customers can search through months of browser and server-side log data in under a second thanks to the tech behind ClickHouse.
[IMG: Quote]
ClickHouse was perfect as Big Data Storage for our ML models
[IMG: Quote]
We store approximately 3 billion events (rows) per day at a rate of approximately 2 million events per minute. We also have to serve some pretty complex data visualizations that depend heavily on filtering very large amounts of data and calculating complex aggregations in a reasonably fast time frame for the sake of the user experience.
[IMG: Quote]
At Sony Entertainment Television, we ingest tens of millions of CDN records into ClickHouse Cloud and run millions of queries against them daily. This allows our operations team to monitor the delivery of our content in real-time, and analyze/investigate potential issues the moment they arise. ClickHouse Cloud has helped us to optimize costs and ensure the high availability and resilience of our services.
[IMG: Quote]
QRadar Log Insights uses a modern open-source OLAP data warehouse, ClickHouse, which ingests, automatically indexes, searches and analyzes large datasets at sub-second speed. You get near real-time visibility and insights from your ingested data.
[IMG: Quote]
The platform is ingesting millions of logs per second from thousands of services across regions, storing several PBs worth, and serving hundreds of queries per second from both dashboards and programs.
[IMG: Quote]
ClickHouse is a fast and highly performant analytical database, widely used across Instacart to power other use-cases such as critical retailer and ads dashboards, calculating results for A/B testing, and machine learning signals.
[IMG: Quote]
We evaluated more than a dozen different big data systems before settling on ClickHouse.
[IMG: Quote]
ClickHouse’s performance exceeds all other column-oriented database management systems.
[IMG: Quote]
We collect tens of thousands of data points from customers’ phones and other more traditional sources. ClickHouse is used as a way to process all of these SMS messages and extract valuable information used for the scoring and fraud models.
[IMG: Quote]
Moving from Elasticsearch to ClickHouse was a long journey, but this is one of the best tech decisions we ever took.
[IMG: Quote]
At Lyft, we ingest tens of millions of rows and execute millions of read queries in ClickHouse daily with volume continuing to increase. On a monthly basis, this means reading and writing more than 25TB of data.
[IMG: Quote]
Cognitiv uses ClickHouse to power their ML offline feature store for its blazing speed and resource efficiency.
“Training these models requires immense computational power and the ability to handle and analyze vast quantities of data quickly and efficiently.
As a smaller company with large datasets, cost is important to us,” explains Jason from Cognitiv. “ClickHouse is fast, but its real value is in letting us better utilize our resources. Basically, we don’t need to spend as much money to solve the same problem.”
[IMG: Quote]
“By utilizing expert models and embeddings, we detect substantive changes in web pages and identify connections between pages that share similar characteristics.”
[IMG: Quote]
ClickHouse has proved to be a game-changer, propelling us towards greater efficiency and effectiveness in managing our data infrastructure.
Ved Surtani, VP, Engineering, Platform & Architecture at Tekion
[IMG: Quote]
We had a billion rows to store...
[IMG: Quote]
Adopting ClickHouse has enhanced our data analytics capabilities, supporting the growing demands of our internal teams efficiently and cost-effectively. Frank Chen, Expert OLAP Engineer at Shopee
[IMG: Quote]
Switching to a Kafka and ClickHouse-based architecture simplified our operations and reduced costs by enhancing performance and enabling real-time, large-scale data processing
[IMG: Quote]
We have saved costs, savings not to be sniffed at, but that was not the driving factor. This was a qualitative step. We just could not do the things we wanted until we had ClickHouse and that is why we’re so excited about it.
[IMG: Quote]
In the post-evaluation of each database against our criteria (with metrics ranging from query performance to cost), ClickHouse emerged as the unrivaled frontrunner. It excelled across the board, even astonishingly so in certain domains, and proved more cost-efficient.
[IMG: Quote]
With ClickHouse, the data pipeline logic is simplified, and is only dealing with the “streaming” aspect of the write as opposed to all of these complexities. ClickHouse thus enables a simpler write design pattern just like any other new age data lake systems like Hudi etc. but with a more simplistic developer experience.
[IMG: Quote]
At DeepL, we use ClickHouse as our central data warehouse.
[IMG: Quote]
Best technical decision we ever made
[IMG: Industries Icon]
[H2] Industries
Learn how leading companies use ClickHouse for real-time analytics, machine learning, data warehousing, and observability across key industries.Explore industries ->->
[IMG: Financial services]
Financial servicesTrading and market analytics, fraud detection, risk monitoring, blockchain, and more.
[IMG: Marketing and sales]
Marketing and salesData store for Adtech, web analytics, SEO, and much more.
[IMG: E-commerce and retail]
E-commerce and retailReal-time inventory monitoring and overall tracking for online businesses.Find out more ->->
[IMG: Technology]
TechnologyIncluding IoT, Energy, Biotech, Manufacturing, and others.
[IMG: Media and entertainment]
Media and entertainmentAssess the performance of videos, assets, and other media in real-time.
[IMG: Gaming]
GamingUnderstand player behavior, gaming dynamics, and other key insights used to improve overall gameplay.Find out more ->->
[IMG: Cybersecurity]
CybersecurityProactive threat detection and response with real-time speed, at any scale.Find out more ->->
[IMG: Automotive]
AutomotiveDeliver vehicle telemetry, factory analytics, predictive maintenance, and connected car insights in real time.Find out more ->->
[IMG: Energy]
EnergyGrid optimization, predictive maintenance, asset performance, and real-time insights across energy operations.Find out more ->->
[H2] Get started for free
We'll get you started on a 30 day trial and $300 credits to spend at your own pace.Create a free account