Plain-English Summary
A Gemini embedding model for converting content into vectors for search, recommendations, and RAG.
Gemini Embedding 2
A Gemini embedding model for converting content into vectors for search, recommendations, and RAG.
Gemini Embedding
Embedding
Stable
Open weights: No
API: Yes
Technical Notes
Multimodal embedding model designed to map content into a shared semantic vector space.
Best For
Semantic search, multimodal retrieval, recommendations, clustering
Watch Out For
Embeddings require a vector database and domain-specific evaluation.
Model Specs
- Maker
- Country
- Not listed
- Family
- Gemini Embedding
- Type
- Embedding
- Release date
- Not listed
- Date confidence
- Not publicly stated
- Status
- Stable
- Context window
- Varies
- Max output
- Not listed
- Parameters
- Not disclosed
- Active parameters
- Not disclosed
- Architecture
- Proprietary multimodal embedding model
- Reasoning
- Not applicable
- Tool calling
- No
- Structured output
- Embedding vector
- API available
- Yes
- Open weights
- No
- Self-hostable
- No
- License
- Proprietary
- Inputs
- Text and supported multimodal content
- Outputs
- Embedding vector
- Approx. price
- See provider pricing
- How to access
- Provider website or API
- Model / API ID
- gemini-embedding-2
- Knowledge cutoff
- Not publicly disclosed
- Fine-tuning
- Prompting / RAG
- Completeness
- 76 %
- Verified
- Jul 18, 2026
- Snapshot date
- Jul 18, 2026
- Source
- Official source