AI Model Catalogue

Embed English — available via AWS Bedrock (us-east-1).

Embed Multilingual — available via AWS Bedrock (us-east-1).

Rerank 3.5 — available via AWS Bedrock (us-east-1).

Embed v4 — available via AWS Bedrock (us-east-1).

Command R — available via AWS Bedrock (us-east-1).

Command R+ — available via AWS Bedrock (us-east-1).

Cohere's multilingual embeddings supporting 100+ languages for global semantic search.

Cohere's latest multimodal embedding model supporting text and images for advanced semantic search.

State-of-the-art English text embedding model for semantic search, clustering, and classification.

This lightweight text embedding model excels at converting English text into numerical vectors for semantic search, clustering, and similarity tasks with minimal computational overhead, making it ideal for developers and organizations seeking cost-effective embedding solutions for applications with resource constraints or latency requirements.

This lightweight multimodal embedding model excels at converting images and text into comparable vector representations for retrieval and similarity tasks, making it ideal for developers and organizations seeking efficient image-text search, clustering, and classification with lower computational requirements.

A large language model with 288K token context designed for enterprise applications requiring complex reasoning, multi-document analysis, and long-form content generation, suitable for organizations needing production-grade performance across customer support, content creation, and knowledge work tasks.

This lightweight Arabic language model with 128K token context is designed for Arabic-speaking developers and organizations seeking efficient performance on Arabic NLP tasks including translation, summarization, and question-answering without requiring extensive computational resources.

This advanced reasoning model with a 289K token context window excels at complex problem-solving, multi-step analysis, and long-document processing, making it ideal for researchers, developers, and professionals who need deep reasoning capabilities and extended context understanding.

command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...

command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...

Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...