Gemini Embedding

Text embedding model: text only in, up to 2,048 tokens, vector of 128 to 3,072 dimensions out. A text-only model. It unifies the earlier text-embedding-005 and text-multilingual-embedding-002.

Understands

text

This model cannot see images or video — you can only give it text. That matters if you planned to show it screenshots or documents with pictures.

Produces

embeddings

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.