Embedding Models

Compare Models

Compare text and multimodal embedding models from Jina, Qwen, Google, OpenAI and more

Jina Embeddings v4

Jina AI
DenseLate

Universal embedding model for multimodal and multilingual retrieval. Supports both single-vector and...

2K dimensions33K tokens$0.050/1M

Jina Embeddings v3

Jina AI
Dense

Multilingual embeddings with task-specific LoRA adapters. Optimized for text retrieval, semantic mat...

1K dimensions8K tokens$0.020/1M

Qwen3-Embedding-8B

Qwen
Dense

State-of-the-art multilingual text embedding model. #1 on MTEB multilingual leaderboard. Supports 10...

4K dimensions33K tokens

Gemini Embedding 001

Google
Dense

Google's text embedding model for semantic search, classification, and clustering. Supports flexible...

3K dimensions2K tokens$0.150/1M

mxbai-embed-large-v1

Mixedbread
Dense

SOTA BERT-large sized embedding model. Outperforms OpenAI text-embedding-3-large and matches models ...

1K dimensions512 tokens

Cohere Embed v4

Cohere
Dense

Multimodal embedding model for text, images, and PDFs. Supports flexible dimensions and 128K context...

2K dimensions128K tokens

Cohere Embed English v3

Cohere
Dense

English-optimized text and image embedding model. Fast and accurate for classification and retrieval...

1K dimensions512 tokens

Cohere Embed Multilingual v3

Cohere
Dense

Multilingual embedding model supporting 100+ languages. Ideal for cross-lingual retrieval and classi...

1K dimensions512 tokens

Voyage 3 Large

Voyage AI
Dense

State-of-the-art general-purpose and multilingual embedding. Outperforms OpenAI-v3-large by 9.74% ac...

2K dimensions32K tokens

GTE-Qwen2-7B-instruct

Alibaba
Dense

Top-ranked embedding model on MTEB English and Chinese. Built on Qwen2-7B with bidirectional attenti...

4K dimensions32K tokens

Linq-Embed-Mistral

Linq AI
Dense

Top retrieval model on MTEB, ranking #1 with 60.2 score. Built on Mistral-7B with advanced data refi...

4K dimensions4K tokens

LFM2-ColBERT-350M

Liquid AI
LateColBERT

Late interaction retriever with excellent multilingual and cross-lingual performance. Fast inference...