Zilliz Cloud Now Available in AWS Asia Pacific (Seoul)
We are excited to announce that Zilliz Cloud is now available in AWS ap-northeast-2 (Seoul). If you're running AI workloads on AWS in Korea — or serving Korean end users from abroad — you no longer need to route through Tokyo or Virginia. Production vector search now runs where your infrastructure already lives.
South Korea is one of the fastest-moving AI markets in Asia, with major internet platforms, gaming studios, and fintech companies shipping AI-native products at scale. AWS ap-northeast-2 is the default region for most of them, and Zilliz Cloud now sits right next to it.
With this launch, teams building in Korea get:
- Lower-latency vector search for Korean users. Teams previously routing to ap-northeast-1 (Tokyo) or US regions can now serve retrieval-augmented generation (RAG), agentic search, recommendation, and semantic search workloads from Seoul — cutting round-trip latency significantly for Korean end users.
- Data residency within South Korea. For organizations subject to Korea's Personal Information Protection Act (PIPA) or internal data governance policies, keeping vector data in-country is now straightforward. Deploy in ap-northeast-2 and your data stays in Seoul.
- One-step migration from wherever you are today. Moving from Pinecone, Qdrant, Weaviate, Elasticsearch, PostgreSQL, OpenSearch, or self-hosted Milvus? Our migration service handles the heavy lifting, so switching to a Seoul-hosted deployment doesn't mean rebuilding your pipeline.
Strengthening Our APAC Footprint
Seoul joins Tokyo, Singapore, and Sydney in our Asia-Pacific lineup on AWS — giving APAC teams four regional options on a single cloud provider. Combined with GCP and Azure coverage in the region, Zilliz Cloud now offers the broadest APAC presence of any managed vector database on the market.
A snapshot of our APAC regions:
| AWS | Google Cloud | Microsoft Azure |
|---|---|---|
| ap-northeast-1 (Tokyo) | asia-southeast1 (Singapore) | Central India (Pune) |
| ap-northeast-2 (Seoul) — New | ||
| ap-southeast-1 (Singapore) | ||
| ap-southeast-2 (Sydney) |
With Seoul live, Zilliz Cloud is now available in 31 regions across AWS, Google Cloud, Microsoft Azure, Alibaba Cloud, and Tencent Cloud. See the full list in our Cloud Providers & Regions documentation.
Get Started with Zilliz Cloud in Seoul
Spinning up a cluster in the new Seoul region takes just a few steps:
- Sign in to Zilliz Cloud — or create a free account if you're new. You can get $100 in credits upon registration with a business email.
- Create a cluster, select AWS as your cloud provider, and choose ap-northeast-2 (Seoul) as your region.
- Configure and deploy — your cluster will be ready in minutes.
If you're migrating from another vector database or moving from a different region, our migration guides and support team are here to help.
What's Next
Our regional expansion doesn't stop here. We're continuously evaluating new regions and cloud providers to meet you where your business operates.
Have a region you'd like to see next? Let us know — your input directly shapes our roadmap.
Fendy FengFendy Feng is the Product Marketing Manager at Zilliz. She has extensive experience developing and enhancing the impact of open-source projects in various global markets by producing high-quality, tailored content. Before joining Zilliz, Fendy worked as a Content Strategist at PingCAP, a fast-growing E-Series startup renowned for its open-source distributed SQL database.
Keep Reading
How to Improve Retrieval Quality for Japanese Text with Sudachi, Milvus/Zilliz, and AWS Bedrock
Learn how Sudachi normalization and Milvus/Zilliz hybrid search improve Japanese RAG accuracy with BM25 + vector fusion, AWS Bedrock embeddings, and practical code examples.
Why Teams Are Migrating from Weaviate to Zilliz Cloud — and How to Do It Seamlessly
Explore how Milvus scales for large datasets and complex queries with advanced features, and discover how to migrate from Weaviate to Zilliz Cloud.
OpenAI o1: What Developers Need to Know
In this article, we will talk about the o1 series from a developer's perspective, exploring how these models can be implemented for sophisticated use cases.