Command R

General language model Generally available Open Weights

Cohere's 35B open-weights model designed for cost-effective enterprise RAG, search grounding, and multilingual workflows.

Overview

Command R (updated snapshot `command-r-08-2024`) is a 35-billion parameter language model developed by Cohere in March 2024 and updated in August 2024. Optimized for enterprise RAG and lightweight agentic execution, Command R provides high accuracy in grounded response generation. The model features a 128,000-token context window with up to 4,096 output tokens. It natively integrates with external search engines, databases, and APIs to generate verifiable citations in response outputs. Command R is accessible via Cohere's hosted API ($0.15 / 1M input tokens, $0.60 / 1M output tokens). Open weights are downloadable under CC-BY-NC 4.0 for non-commercial research.

Technical Specifications

Context Window 128,000 tokens
Max Input Tokens 128,000
Max Output Tokens 4,096
Parameters 35.0B
Released 2024-03-14

Modalities

Text → Text (Both)

Capabilities

Text Generation Code Generation RAG Function Calling Long Context

Use Cases

Customer Support Business Analysis Document Processing

Languages

English (en) Spanish (es) French (fr) German (de) Chinese (zh)

Access Routes

Route Type Protocol Region / Scope Provider Status
Cohere Hosted API (Direct provider) Cohere REST API Cohere Available

Provider

Cohere

Family: Command

Identifiers

  • command-r Canonical identifier Default
  • command-r-08-2024 Canonical identifier Default
  • cohere/Command-R Repository identifier Default

Compare

See how this model stacks up against others.

Compare with Other Models

Platform Status

Optix AI is under active development. Verified model records, pricing schemas, deployment guides, and published benchmark data are being added progressively. Our mission is to provide transparent AI model discovery and comparison with clearly sourced facts.

Data Verification: Ongoing curation and manual verification of model specifications against official sources.
Regular Updates: Addition of newly released commercial and open-source models as records are verified.
Developer First: Built with transparency, clearly sourced facts, and community feedback.