Best embedding AI models

7 embedding models compared on specs, pricing and community reviews.

• text-embedding-3-small — openai: Text-embedding-3-small is OpenAI's highly efficient and cost-effective embedding model designed to convert textual data into numerical vectors. It offers a sign
• text-embedding-004 — google: text-embedding-004 generates vector representations for text used in search, clustering and classification. It's accessible via the Gemini API. It supports task
• Gemini Embedding 2 — google: Google's first multimodal embedding model — text, image, video, audio and PDFs in one space. $0.20 per 1M text input tokens.
• text-embedding-3-large — openai: Text-embedding-3-large is OpenAI's flagship embedding model, engineered to provide highly accurate vector representations for complex semantic search and retrie
• Embed v4 — cohere: Embed v4 generates unified embeddings for text, images and mixed documents (like PDFs with charts), supporting a 128k token context. It's designed for enterpris
• Voyage-3-large — voyage ai: voyage-3-large delivers state-of-the-art retrieval quality across domains including code, legal and finance, with flexible output dimensions and quantization op
• Cohere Rerank 3.5 — cohere: Rerank 3.5 improves search relevance by reordering candidate documents using reasoning and better multilingual understanding. It supports 100+ languages and a 4