All models
OpenAI
Text Embedding 3 Small
OpenAI's compact embeddings
This model is not in the catalog right now.
See available modelsAbout the model
Text Embedding 3 Small is OpenAI's compact embeddings model, aimed at cheap, fast vector generation. It turns text into representations for semantic search and RAG at low cost and high throughput, which is convenient at large volumes. The model supports adjustable vector dimensions, so you can choose the trade-off between accuracy and storage footprint. The resulting vectors work well for clustering, recommendations, deduplication and classification. It handles many languages confidently, including Russian.
Strengths
- Cheap, fast vector generation
- Adjustable vector dimensions
- High throughput at volume
- Vectors for clustering and recommendations
- Suited to RAG and semantic search
- Works in many languages, including Russian
Where to use it
- Semantic search across documents
- RAG pipelines and question-answering systems
- Clustering and topic grouping
- Recommendation systems
- Deduplication and similarity search
- Vector-based text classification