Question 1

What's the difference between a foundation model and a traditional machine learning model?

Accepted Answer

A traditional ML model is usually trained for one specific task (like spam detection) using task-specific labeled data. A foundation model is trained on broad data to learn general language or vision patterns, then adapted to many tasks using prompting, retrieval (RAG), or fine-tuning—often with far less task-specific training.

Question 2

When should I use a foundation model?

Accepted Answer

Use a foundation model when you need flexible capabilities such as summarization, chat, content generation, code help, classification, or embeddings—and you want to build quickly without training a model from scratch. It’s especially useful when requirements change often or you need one system to handle many related tasks.

Question 3

How much does a foundation model cost?

Accepted Answer

Costs typically depend on (1) the model you choose, (2) how many tokens or characters you send and receive, (3) whether you use embeddings, fine-tuning, or tools like retrieval, and (4) throughput/latency needs. Managed services usually charge per input/output token (or per character) and may add charges for hosting fine-tuned models, vector databases, and data egress.

Foundation Model

Definition

Real-World Example

Related Terms

Cloud Provider Equivalencies

Explore More Cloud Computing Terms