Home/Models/Command R+

Command R+

by Cohere· Released 2024-04
Official Docs ↗

Command R+ is Cohere's flagship model optimized for retrieval-augmented generation. Its native grounding with document citations makes it the top choice for enterprise RAG pipelines where accuracy and source attribution are critical.

Input Price
$2.50/1M
per 1M tokens
Output Price
$10.00/1M
per 1M tokens
Context Window
128K tokens
max tokens
ELO Score
1230
LMSYS Arena

Pricing Breakdown

VolumeInput CostOutput CostCombined (50/50)
1,000 tokens$0.0025$0.0100$0.0063
10,000 tokens$0.0250$0.1000$0.0625
100,000 tokens$0.2500$1.0000$0.6250
1,000,000 tokens$2.5000$10.0000$6.2500

Strengths

  • Best-in-class retrieval-augmented generation (RAG)
  • Native document grounding with citations
  • Strong for enterprise knowledge bases
  • Multi-hop retrieval capability

Weaknesses

  • Less capable at open-ended creative tasks
  • Smaller community vs. OpenAI

Best For

researchdocument analysisdata extractioncustomer support

Compare Command R+ With

Command R+ vs o3
OpenAI
Command R+ vs DeepSeek R1
DeepSeek
Command R+ vs o1
OpenAI
Command R+ vs Gemini 2.0 Flash
Google
Command R+ vs DeepSeek V3
DeepSeek
Command R+ vs Claude Sonnet 4.6
Anthropic

Frequently Asked Questions

How much does Command R+ cost?

Command R+ costs $2.50/1M per 1M input tokens and $10.00/1M per 1M output tokens.

What is Command R+'s context window?

Command R+ has a context window of 128K tokens, which means it can process up to 128,000 tokens in a single request.

Is Command R+ open source?

No, Command R+ is a proprietary model by Cohere and is not open source.

What is Command R+ best used for?

Command R+ is best suited for: research, document-analysis, data-extraction, customer-support. Best-in-class retrieval-augmented generation (RAG).

What is Command R+'s ELO score?

Command R+ has an ELO score of 1230 on the LMSYS Chatbot Arena leaderboard, placing it in the mid-tier range.