Vertex AI pricing varies by service, with core costs determined by model training, prediction (online and batch), and storage. For example, custom training is often priced per node-hour, online predictions can be priced per 1,000 counts, and generative AI models are priced per 1 million tokens.

Finout is a financial technology (fintech) company focused on providing innovative solutions for personal finance management, budgeting, and investment tracking. Through their blog, Finout shares tips, guides, and insights on financial planning, wealth management, and investment strategies. Readers can learn about budgeting techniques, investment principles, and ways to optimize their financial health and achieve their long-term financial goals.

finout

Vertex AI pricing varies significantly across 16 core services including generative AI models (Gemini variants priced per million tokens), custom training (per node-hour), predictions (per 1,000 counts), and supporting services like pipelines, feature stores, and vector search. Gemini models range from $0.10 to $120 per million tokens depending on variant and context length. Training costs depend on machine types and accelerators, with GPU instances ranging from $0.64 to $105 per hour. Cost optimization strategies include prompt engineering to reduce token usage, selecting appropriate model families, implementing caching and batching, and controlling regional deployment footprint.

Vertex AI: Pricing for Top 16 Vertex Services in 2026

Google Vertex AI Pricing: Generative and Agentic AI

Google Vertex AI Pricing: Forecasting and Prediction

Google Vertex AI Pricing: Supporting AI Services

Cost Optimization Strategies for Vertex AI Costs