Introducing Cohere’s enterprise foundation models
Benefits
Meet Cohere
Cohere's partnership with AWS brings together advanced generative AI and search optimization capabilities through Amazon Bedrock. These models enable enterprises to build powerful generative AI applications that transform how organizations access and utilize information. Hear from Saurabh Baji, CTO of Cohere, as he explains how Cohere models in Amazon Bedrock create unique customer value through frictionless development and robust enterprise security.
Use cases
Model version
Rerank 3.5
Rerank 3.5 enhances search accuracy by reranking keyword and vector results. This ensures that only the most relevant content reaches the model—delivering better responses while reducing both latency and costs.
Max tokens: 4,096
Languages: 100+ languages including English, Chinese, Korean, Hindi, Japanese, Spanish, German, French, Arabic, Russian, and Portuguese
Fine-tuning supported: No
Supported use cases: Search-heavy, document-heavy, and RAG scenarios (for example, searching for a hotel)
Command R+
Command R+ is Cohere's most powerful generative language model optimized for long-context tasks, such as RAG and multi-step tool use.
Max tokens: 128K
Languages: English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Arabic, and Chinese
Fine-tuning supported: No
Supported use cases: Text generation, text summarization, chat, knowledge assistants, Q&A, RAG
Command R
Command R is Cohere's generative language model optimized for long-context tasks, such as RAG and tools and large scale production workloads.
Max tokens: 128K
Languages: English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Arabic, and Chinese
Fine-tuning supported: No
Supported use cases: Text generation, text summarization, chat, knowledge assistants, Q&A, RAG
Command
Command is Cohere’s generative large language model (LLM).
Max tokens: 4K
Languages: English
Fine-tuning supported: Yes
Supported use cases: Chat, text generation, text summarization
Command Light
Command Light is a smaller version of Command, Cohere's generative LLM.
Max tokens: 4K
Languages: English
Fine-tuning supported: Yes
Supported use cases: Chat, text generation, text summarization
Embed 3 Multilingual
Embed 3 is Cohere's advanced text and image representation, or embeddings, model. This version supports 100+ languages and delivers exceptional performance for cross-lingual semantic search and retrieval tasks.
Max tokens: 512
Languages: Multilingual (100+ supported languages)
Fine-tuning supported: No
Supported use cases: Semantic search, RAG, classification, clustering, multimodal search and retrieval
Embed 3 English
Embed 3 is Cohere's advanced text and image representation, or embeddings, model. This version supports English only and delivers exceptional performance for semantic search and retrieval tasks.
Max tokens: 512
Languages: English
Fine-tuning supported: No
Supported use cases: Semantic search, retrieval-augmented generation (RAG), classification, clustering, multimodal search and retrieval.