gemini-embedding-2-preview

by Google

Google's first multimodal embedding model .aihubmix does not currently support multimodal input; support is expected next week.perfectly meeting the need for fast, scalable similarity computation on large-scale multimodal datasets.

API Pricing

Input

$0.2 / 1M tokens

Specifications

Modalities

text, image, audio, video

More from Google

• gemini-3.1-flash-lite-image
• gemini-3.5-flash
• gemini-3.1-flash-image
• gemini-3-pro-image
• gemini-3.1-flash-lite
• gemini-3.1-flash-lite-nothink
• gemma-4-26b-a4b-it
• gemma-4-31b-it

Use gemini-embedding-2-preview via the AIHubMix unified API — one interface for every major LLM.