Jina Embeddings v3
8K context multilingual embedding with task-specific LoRAs
Verdict
Long context embeddings up to 8192 tokens — ideal for document-level retrieval. Task-specific LoRA adapters for retrieval, classification, and similarity. Good API and open weights.
Other Embedding Models
- BGE-M3Stable
BAAI multi-granularity multilingual embedding with dense + sparse
- Cohere Embed v3Production
Multilingual embedding model optimised for search and RAG
- E5-Mistral-7BStable
Large LLM-based embedding model for maximum retrieval quality
- GTE-Qwen2Experimental
Alibaba's embedding model with strong CJK language support
- Mixedbread EmbedExperimental
Emerging high-quality embedding model from Berlin-based lab
- Nomic Embed v1.5Stable
Fully open-source embedding model with Matryoshka support