Text Multilingual Embedding 002

Multilingual embedding model: text only in, up to 2,048 tokens, vector of up to 768 dimensions out. A text-only model.

Legacy: вендор до сих пор даёт выбрать её в Vertex AI, но объединил её возможности в gemini-embedding-001. Месяц выхода на страницах вендора не указан.

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.