Command R (08-2024)

About Command R (08-2024)

Command R is Cohere's efficient RAG-optimized model, delivering strong retrieval-augmented generation capability at accessible pricing. With 35 billion parameters, it offers excellent performance on grounded generation tasks while being more cost-effective than Command R+. The model excels at synthesizing information from provided documents, producing accurate responses with proper citations. Command R features a 128K context window and supports Cohere's RAG infrastructure including document ingestion and retrieval. It's particularly valuable for high-volume enterprise applications where RAG capability matters but flagship pricing isn't justified for every request. The model supports function calling and tool use, enabling sophisticated AI workflows. Command R integrates with Cohere's embedding models for complete retrieval pipelines. For organizations building production RAG systems at scale, Command R provides the specialized capability needed for accurate, grounded AI responses without premium costs. It serves as the workhorse model for many enterprise knowledge management and customer support deployments.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Cohere Model Lineup

Compare all models from Cohere to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Qwen2.5 VL 72B Instruct

Alibaba Qwen

Input: $0.15

Output: $0.60

Context: 33k

Qwen3 VL 30B A3B Instruct

Alibaba Qwen

Input: $0.15

Output: $0.60

Context: 131k

Llama 4 Maverick

Meta

Input: $0.15

Output: $0.60

Context: 1.0M

GPT-4o-mini Search Preview

OpenAI

Input: $0.15

Output: $0.60

Context: 128k

💡 Cheaper Alternatives

Same Brand (Cohere)

Cross Brand

🚀 Quick Start

Get started with Command R (08-2024) API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="cohere/command-r-08-2024",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision