AI API cost glossary

Embedding tokens

Embedding tokens are input tokens processed by an embedding model to create vector representations for search, clustering, or retrieval.

Why it matters for API cost

Embedding cost scales with corpus token volume and re-indexing frequency. Chunk overlap can embed the same text repeatedly.

embedding cost = embedded tokens ÷ 1,000,000 × embedding input rate

Ten million corpus tokens at $0.02 per million tokens cost an estimated $0.20 for one full embedding pass.

Are embedding and vector storage the same cost?

No. Embedding creates vectors; a vector database separately charges for storage, queries, compute, or replicas.

How to Calculate LLM Tokens and Estimate API Cost

Learn how to estimate LLM tokens, convert input and output usage into API cost, and build a realistic monthly AI budget.

OpenAI API Pricing Explained: Tokens, Cache, Batch, and Cost

Understand OpenAI API input, output, cached input, batch, image, audio, and embedding pricing with practical formulas.