Cohere · Command R
Command R+
Cohere's enterprise RAG specialist with clean tool calling.
Command R+ is the model built around retrieval and tool-calling rather than topping a leaderboard. For enterprise teams shipping RAG pipelines where citation accuracy matters more than benchmark scores, it's a credible non-OpenAI choice - and the open weights mean you're not locked in.
Specs
- Context window
- 128K tokens
- Input ($/1M tokens)
- $2.50
- Output ($/1M tokens)
- $10.00
- Modalities
- Text
- Released
- Apr 4, 2024
- Weights
- Open
Capabilities
- Tool use
- Vision
- Extended thinking
- Prompt caching
- Open weights
API model id
command-r-plus
Vendor docs: docs.cohere.com
Compare Command R+ with
Command R+ vs Claude Opus 4.8
Anthropic's heavyweight for hard reasoning and agentic work.
Command R+ vs Claude Sonnet 4.6
The pragmatic default - Claude quality without Opus pricing.
Command R+ vs Claude Haiku 4.5
Fast, cheap, surprisingly capable for high-volume jobs.
Command R+ vs GPT-5.4
OpenAI's flagship - broadest modality and ecosystem coverage.
Command R+ vs GPT-5.4 Mini
GPT-5 economics for high-volume routine tasks.
Command R+ vs o3
OpenAI's mainstream reasoning model - production-viable thinking.