Snowflake Cortex
AI and LLM capabilities built directly into Snowflake's data cloud
Overview
AI features built into Snowflake's cloud data platform. Cortex provides LLM functions, vector search, ML model deployment, and AI-powered data analysis directly within Snowflake SQL — no data movement required.
Ehsan's Growth Verdict
Smart play — bringing AI to the data instead of moving data to the AI
Best for: Snowflake customers who want AI capabilities without building separate ML infrastructure
Key Features
- ✓LLM functions in SQL
- ✓Vector search and embeddings
- ✓Document AI extraction
- ✓Cortex Analyst for natural language queries
- ✓Serverless ML model deployment
Pros
- + Run AI where your data already lives — no ETL needed
- + SQL interface means analysts can use AI without Python
- + Enterprise-grade governance and security
Cons
- − Credits system makes cost forecasting difficult
- − AI features less mature than Databricks MLflow
- − Locked into Snowflake as your data platform
Pricing
| Plan | Details |
|---|---|
| Compute | Credit-based ($2-4/credit) |
| Storage | $23-40/TB/mo |
| Cortex AI | Per-token pricing varies by model |
Best Use Cases
Ehsan's Growth Take
Snowflake Cortex makes AI accessible to SQL-fluent analysts who would never open a Jupyter notebook. For companies where the data already lives in Snowflake, the zero-data-movement advantage is real and saves weeks of pipeline work.
Ehsan Jahandarpour
AI Growth Strategist & Fractional CMO
Forbes Top 20 Growth Hacker · TEDx Speaker · 716 Academic Citations · Ex-Microsoft · CMO at FirstWave (ASX:FCT) · Forbes Communications Council