LLM Reference

Command R Models by Cohere

CohereCC-BY-NC-4.0Open weightsHighlightOpen Source
2 models2024Up to 128k ctxFrom $0.15/1M input

Details

ResearcherCohere
Commercial useNon-commercial only
Models2
Released2024
Max context128k

Capabilities

Structured OutputsAll models

About

Command R is a large language model optimized for conversational interaction and long context tasks. It targets the “scalable” category of models that balance high performance with strong accuracy, enabling companies to move beyond proof of concept and into production.

Current Variants

Use-when guidance is derived from seed capabilities, context, release, and replacement fields.

1 in view1 retired
Command R+Current

Use when the workload needs 128k context and structured outputs.

2024-04128k contextstructured outputs

Release Timeline

1 release group
2024-04
1 current · 1 retired
Command R
128k contextstructured outputs
Archived
Command R+
128k contextstructured outputs
Current

Specifications(2 models)

Command R model specifications comparison
ModelReleasedContextParametersStructured Outputs
Command R+2024-04128k104B*Yes

Pricing

Command R model pricing by provider
ModelProviderInput / 1MOutput / 1MType
Command R+Cohere API$2.5$10Serverless
Command R+OpenRouter$2.5$10Serverless
Command R+AWS Bedrock$3$15Serverless
Command R+Microsoft Foundry$3$15Serverless

Frequently Asked Questions

What is Command R used for?
Command R is used for structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
How does Command R compare to Command?
Command R by Cohere is strongest where you need structured outputs, while Command by Cohere is the closest related family to check for multilingual. Command R has 2 listed variants and reaches up to 128k context, while Command reaches up to 256k context, so compare the specs and pricing tables before choosing a production model.
Which Command R model should I use?
For the lowest listed input price, start with Command R through OpenRouter at $0.15/1M input tokens. For the most capable/latest local choice, evaluate Command R+ with 128k context and structured outputs.

Models(2)