Cohere Embed v4vsAya 23 35B

Cohere Embed v4, developed by Cohere, is the first multimodal embedding model in Cohere's lineup, processing both text and images into unified 128K-context vector representations. The model generates embeddings for semantic search, RAG pipelines, document retrieval, and visual search applications. Supporting 100+ languages, Embed v4 produces compact, efficient vectors optimized for modern vector databases. Its multimodal capability enables searching across mixed document types containing both text and visual elements. Priced at $0.12 per million tokens, it offers affordable embedding generation for production applications. The model represents a significant upgrade over text-only Embed v3, enabling unified search across document types. It is particularly valuable for enterprises with heterogeneous content including PDFs, presentations, and image-heavy documents that require combined text and visual understanding.

Aya 23 35B, developed by Cohere through the Cohere For AI research initiative, is an open-source multilingual model with 35 billion parameters and an 8K token context window supporting 23 languages. The model was developed with contributions from researchers worldwide, focusing on extending quality AI capabilities to lower-resource languages that mainstream models underserve. Aya 23 35B performs well on multilingual benchmarks, particularly for languages in Africa, South Asia, and Southeast Asia where few commercial alternatives exist. Free and open-source, it can be fine-tuned and deployed for language-specific applications without cost. The model represents Cohere's commitment to democratizing AI access globally, providing a foundation for researchers and developers working in languages outside the English-Chinese-European focus of most commercial models.