Snowflake Cortex AI
Snowflake Cortex AI is a suite of fully managed generative AI services built into Snowflake, providing LLM access, hybrid search, RAG pipelines, and AI agents without moving data outside the Snowflake security perimeter.
Description
Snowflake Cortex AI is a fully managed suite of AI services natively integrated into the Snowflake Data Cloud. It provides SQL-based and REST API access to large language models (LLMs) from leading providers including Anthropic, Meta, Mistral AI, OpenAI, and DeepSeek. All models run within Snowflake's infrastructure, so data never leaves the platform's security perimeter.
Core components include Cortex Search (hybrid vector and lexical search), Cortex Agents (AI agent orchestration), Cortex Fine-tuning (model fine-tuning on proprietary data), Cortex Analyst (natural language analytics), and Cortex AI Guardrails (content safety filtering). These capabilities integrate with Snowflake ML, which provides a model registry, feature store, ML pipelines, and model observability.
Snowflake Cortex AI operates on a serverless model with token-based or provisioned throughput billing. It is available across 34 regions on AWS, Azure, and Google Cloud, with sovereign cloud options and data residency guarantees.
MLOps LifecycleMLOps LifecycleFull model lifecycle: registry, feature store, prompt management, monitoring and human-in-the-loop.
Model Registry
Feature Store
Prompt Management
Monitoring
Human-in-the-Loop
Data & KnowledgeData & Knowledge ManagementData connectors, vector database integration, native vector search and data management (PII, provenance, synthetic data).
ApplicationsAI ApplicationsDomains and use cases this platform is best suited for — from RAG and fine-tuning to scientific research.
SecurityEnterprise SecurityCertifications, access controls and data-protection features essential for corporate deployments and cloud privacy compliance.
Developer EcosystemDeveloper EcosystemDeveloper resources: available SDKs, supported programming languages, and infrastructure features and model-deployment methods.
Pricing & Business ModelPricing & Business ModelBilling models (usage-based, provisioned throughput), resource limits and SLA parameters (uptime, support tiers).
Pricing models
Resource quotas
SLA & Support