Vertex AI Multimodal Embeddings Models by Google DeepMind
Google DeepMindProprietary
1 model2024
Last refreshed 2026-07-01. Next refresh: weekly.
Details
ResearcherGoogle DeepMind
LicenseProprietary
Commercial useCommercial use: conditional
Models1
Released2024
Capabilities
VisionAll models
MultimodalAll models
Links
WebsiteAbout
Google Cloud Vertex AI multimodal embedding models for text, image, and video retrieval.
Decision facts
- Best fit
- embeddingvision and multimodal work
- Capability starting point
- Vertex AI Multimodal Embeddings with multimodal inputs
- Lowest tracked input
- Not tracked
- Closest related family
- T5Gemma
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
Use when the workload needs embedding and multimodal inputs.
2024-08embeddingmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Vertex AI Multimodal Embeddings | Use when the workload needs embedding and multimodal inputs. | 2024-08 | embeddingmultimodal inputs | Current |
Release Timeline
1 release group2024-08
1 current
Vertex AI Multimodal Embeddings
Currentembeddingmultimodal inputs
Specifications(1 models)
| Model | Released | Vision | Multimodal |
|---|---|---|---|
| Vertex AI Multimodal Embeddings | 2024-08 | Yes | Yes |
