Gemini Embedding 2 is Google's natively multimodal embedding model, in preview. It maps text, images, video, audio and PDF documents into a single embedding space across more than 100 languages, accepting up to 8,192 text tokens, with 3,072-dimensional output that can be shortened through Matryoshka Representation Learning.
Modalities
In / out price
$0.25 / $0.25per 1M
Context
2K
Max output
–
Updated
Oct 22, 2026
Providers
1 routeCompare providers by price, privacy, and speed.
| Anonymous | $0.25 | $0.25 | — | 2K | – | — | — |
Privacy
1 / 4Anonymous routing
Anonymous tier
- Anonymous
- Private
- TEE
- E2EE
Your identity is hidden from the inference provider. The inference provider can see prompt content; zero retention is not guaranteed. Learn more
Features
1Embeddings
Uptime
FAQ
Common questions about Gemini Embedding 2 Preview.