Command RvsAya 23 35B

Command R, developed by Cohere, is an enterprise-grade model with 35 billion parameters and a 128K token context window optimized for retrieval-augmented generation. The model specializes in grounded generation, producing responses with accurate citations from provided source documents. It handles document search, summarization, information extraction, and conversational Q&A with built-in citation capabilities. Command R supports 10 languages and features production-ready RAG tooling that reduces hallucination on retrieval tasks. Priced at $0.15 per million input tokens and $0.60 per million output tokens, it offers cost-effective enterprise search capabilities. As an open-source model, it can also be self-hosted. Command R ranks #23 on the Chatbot Arena leaderboard, reflecting its specialized design for retrieval tasks rather than general-purpose benchmarks where broad models score higher.

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.