Google: Gemini Embedding 2 Preview
google/gemini-embedding-2-previewGemini Embedding 2 Preview is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It...
- Context window
- 8,192 tokens
- Input
- text · image · file · audio · video
- Output
- embeddings
- Relay support
- Price book only
Reference prices & points
CNY 1 = 1,000 points. The table shows site reference rates; charges use actual usage. · Price version 2
| Billing unit | Our price / CNY | Points |
|---|---|---|
| Input / 1M tokens | ¥1.72 | 1,720 |
| Output / 1M tokens | ¥0 | 0 |
| Per image | ¥0.00000387 | 0.00387 |
| Audio / 1M tokens | ¥55.9 | 55,900 |
Catalogue rates are for reference. The settled charge uses actual usage for that request, at the price version locked when it was reserved. Caching, long context, images and audio are charged when used. Listed prices do not mean every capability is available through this relay.
Catalogue time: 2026-11-13T20:08:26.195Z · Live catalogue
Integration & availability
This model is listed in the price book but cannot be called from this workspace. The workspace supports text chat, vision and optional web search. Turn on Image mode to find eligible image generators. Other modalities are currently price-book entries.