Compare two models
Select any two models. Input, output, cached, and context rarely move together — the cheaper model on one line isn't always the cheaper one on the next.
Description
Google's Gemini embedding model. Native 3072 dimensions with Matryoshka truncation (e.g. 1536/768/256).
OpenAI's smaller embedding model. Native 1536 dimensions, truncatable via the dimensions parameter down to 512.
Input /1M
$0.15
$0.02
Context
2K
8K
Dimensions
3072
1536
Released
—
Jan 2024
Status
—
—
Provider
Google
OpenAI