Gemini Embedding 2 Model Launch

Google announced the release of gemini-embedding-2-preview, a multimodal embedding model supporting text, image, video, audio, and PDF inputs, replacing the Gemini 3.1 Flash-Lite Preview.

Mar 10, 2026 (UTC)Views:0

View gemini-3.1-flash-lite in Price Matrix Calculate Spend Impact Google AI Overview

Impact Assessment

Cost0

Reliability0

Migration2

Quality4

Compliance0

Sources

changelog

Google AI Changelog

Announcing Gemini Embedding 2 , our first fully multimodal embedding model.

Comments

Loading comments...

AI Cost Optimization

Does this change your best option?

Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.

Check my models Apply for founder pilot