Command R
Command R by Cohere is a text generation model built for conversational interaction, long-context tasks, grounded RAG, tool use, and a 128K context window.
Model Overview
Capabilities, design details, and architectural traits
Command R - Long-context RAG and tool-use model
Command R is Cohere's text generation model, positioned for conversational interaction, long-context tasks, retrieval-augmented generation, and tool use. Cohere documents it as a scalable model for production workloads with grounded generation support and a 128K context window.
Defining Characteristics
| Aspect | Official Characteristic |
|---|---|
| Context | Supports a 128,000-token context window. |
| Retrieval | Built for RAG workflows and grounded generation from supplied document snippets. |
| Tool use | Trained for conversational tool use with JSON-formatted action planning. |
| Languages | Optimized for 10 key languages, with additional pretraining data in 13 more languages. |
| Update impact | The refresh improved tool-use decisions, instruction following, structured data analysis, and robustness to prompt formatting changes. |
Benchmark Performance
Independent evaluations · Artificial Analysis
Accuracy & Capability Details
Compare Models Side-by-Side
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | |||
|---|---|---|---|
| General Info | |||
| Provider | Cohere | Anthropic | Anthropic |
| Release Date | March 12, 2024 | September 22, 2026 | September 28, 2026 |
| Knowledge Cutoff | Mar 2024 | - | Jun 2026 |
| Context & Limits | |||
| Context Window | 128K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | $0.50 Best Input Pricing | $4 | $2 |
| Output Pricing | $1.50 Best Output Pricing | $20 | $10 |
| Modalities | |||
| Inputs | text | textimagefile | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 5.0 | 57.6 Best Intelligence Index | 56.0 |
| Coding Index | - | - | - |
| Agentic Index | - | - | - |
Humanity's Last Exam
Extremely difficult logical reasoning and knowledge.
SciCode Benchmark
Scientific coding and mathematical modeling.
Long Context Reasoning
Logical reasoning over long context windows.
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
Explore more from Cohere
Other models by Cohere
Top AI Models
Leading alternatives by intelligence score
