Embedding and rerank API prices

Embedding and rerank models, priced per million tokens or per query, with every provider.

As of Nov 4, 2026, the cheapest embedding API is pplx-embed-v1-0.6b at $0.004 per million tokens from Perplexity; OpenAI's text-embedding-3-small costs $0.02.

81 embedding models · prices per million tokens from the cheapest provider; open a row for every provider

Rerank models (25)

A reranker scores documents against a query to reorder search results. Providers price it either per query (one query over a set of documents) or per token, so prices are compared only within the same unit.

About this data

Prices come from LiteLLM's model cost map, with more providers from models.dev (both MIT licence), checked Nov 4, 2026. Providers change prices without notice; confirm on their pricing page before you rely on a number. Arena scores: LMArena text leaderboard of 2026-10-28 (CC BY 4.0). Provider logos: Lobe Icons.