- Home
- Ai Databases
- AlloyDB AI
On the recordRead 9 Oct 202614 facts
AlloyDB AI
Plans and prices
AlloyDB for PostgreSQL, pay-as-you-go
Priced on request
CPU and memory · database storage · backup storage · networking
Read 9 Oct 2026 · cloud.google.com
On the record
- Agent connectivity
- AlloyDB includes a fully managed remote MCP server for providing agents access to data.cloud.google.com · read 9 Oct 2026
- AI functions
- AlloyDB AI functions let SQL queries generate embeddings, perform similarity searches, call AI models, analyze sentiment, generate content, and run forecasts.cloud.google.com · read 9 Oct 2026
- Certifications
- Google lists AlloyDB certifications including ISO 27001, ISO 27017, ISO 27018, ISO 27701, SOC 1, SOC 2, SOC 3, PCI DSS, and HIPAA.docs.cloud.google.com · read 9 Oct 2026
- Deployment
- AlloyDB Omni is a downloadable AlloyDB edition for on-premises, air-gapped, edge, or multicloud deployments.cloud.google.com · read 9 Oct 2026
- Encryption
- AlloyDB encrypts cluster data at rest by default and supports customer-managed encryption keys, Cloud KMS Autokey, and Cloud External Key Manager.docs.cloud.google.com · read 9 Oct 2026
- Framework integrations
- The product page names Agent Development Kit, LangChain, and LlamaIndex as orchestration framework integrations.cloud.google.com · read 9 Oct 2026
- Model access
- Users can access Gemini or other foundation models hosted on Gemini Enterprise Agent Platform and register endpoints on any platform for calls from AlloyDB SQL functions.cloud.google.com · read 9 Oct 2026
- Natural language
- QueryData lets data agents translate natural-language questions into SQL and disambiguate questions when needed.cloud.google.com · read 9 Oct 2026
- Network security
- AlloyDB supports TLS 1.3, VPC Service Controls, and private connectivity options; its default endpoint is not publicly routable.docs.cloud.google.com · read 9 Oct 2026
- Notable pricing limit
- CPU and memory are priced per vCPU and GiB, pricing varies by location, and an instance can have up to 288 vCPUs and 2,232 GiB memory per node.cloud.google.com · read 9 Oct 2026
- Purpose
- AlloyDB AI integrates vector embeddings, high-performance vector search, and natural language into a PostgreSQL-compatible database for building AI agents and apps.cloud.google.com · read 9 Oct 2026
- SQL and vector queries
- The ScaNN index integrates with the PostgreSQL query planner, and adaptive filtering coordinates filters, joins, and vector indexes.cloud.google.com · read 9 Oct 2026
- Vector search
- Its ScaNN index supports pgvector-compatible semantic search and is described as scaling to over 10 billion vectors.cloud.google.com · read 9 Oct 2026
- Who it is for
- The product is presented for developers building AI applications and agents grounded in structured and unstructured enterprise data.cloud.google.com · read 9 Oct 2026
