Command R Models by Cohere
2 models2024Up to 128k ctxFrom $0.15/1M input
Details
ResearcherCohere
LicenseCC-BY-NC-4.0
Commercial useCommercial use: non-commercial
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 based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view1 retired
Command R+Current
Use when the workload needs 128k context and structured outputs.
2024-04128k contextstructured outputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Command R+ | Use when the workload needs 128k context and structured outputs. | 2024-04 | 128k contextstructured outputs | Current |
Release Timeline
1 release group2024-04
1 current · 1 retired
Command R
Archived128k contextstructured outputs
Command R+
Current128k contextstructured outputs
Specifications(2 models)
| Model | Released | Context | Parameters | Structured Outputs |
|---|---|---|---|---|
| Command R+ | 2024-04 | 128k | 104B* | Yes |
Available From(6 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Command R+ | Cohere API | $2.5 | $10 | Serverless |
| Command R+ | OpenRouter | $2.5 | $10 | Serverless |
| Command R+ | AWS Bedrock | $3 | $15 | Serverless |
| Command R+ | Microsoft Foundry | $3 | $15 | Serverless |
Popular comparisons in this family
- Command R+ vs Mistral Large 2.1 (2411)41
- Claude 3.5 Haiku vs Command R+22
- Claude 3.5 Sonnet vs Command R+20
- Command R+ vs Mistral Large 219
- Claude 3.5 Sonnet vs Command R8
- Claude 3.5 Haiku vs Command R8
- Command R+ vs GPT-4o-mini Search Preview3
- Command R+ vs Qwen2-7B-Instruct2
- Command R+ vs GPT-4o Mini (07-18)1
- Command R+ vs Together AI Qwen2-7B-Instruct1
Comparisons
- Command R+ vs GPT-4o Mini (07-18)
- Command R+ vs Claude 3.5 Haiku
- Command R+ vs Mistral Large 2.1 (2411)
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.
